Community Spring Cleaning week is here! Join your fellow Maveryx in digging through your old posts and marking comments on them as solved. Learn more here!

Past Analytics Excellence Awards

Suggest an idea

Author: Michael Peterman, CEO In-2CRev-28px-R.png

Company: VeraData

 

Awards Category: Best 'Alteryx for Good' Story

 

We provide deep analytics services for hundreds of clients.  Of particular interest is the NCCS (National Childrens Cancer Society).  This prestigious and highly respected organization has been doing more for the families of children with cancer since 1987 - yep, for almost 30 years.  We are honored to be serving them as a client.

 

Describe the problem you needed to solve 

NCCS, like every other large charity in America, sends out direct mail fundraising solicitations to support these families.  Like any other business has to spend money to acquire new customers, non-profit organizations spend money to acquire donors.  They were faced with a year over year trend of increasing donor acquisition costs and increasing costs to reactivate lapsed donors.   This was coupled with a concern was that there was a shrinking universe of potential donors who were willing to support their efforts.

 

Describe the working solution

Enter VeraData. Our initial engagement with NCCS was to build a donor acquisition model to reduce their costs to acquire donors, which subsequently reduces the cycle time to break-even on the investment in new donors. Concurrently, we developed a lapsed reactivation model that used tons of external, outside information to select from their audience of former donors the individuals most likely to donate again, therefore increasing the universe of marketable names while maintaining the cost to reactivate. Lastly, our third component was to uncover an expanded universe of individuals who had the propensity to support the NCCS. This meant identifying new data sets and determining which individuals would be profitable to pursue.

 

There were several methodologies deployed to achieve these goals. Our analytic team settled on a series of support vector machine models solving for response rate, donation amount, package and channel preferences, etc. All of the information in our arsenal was called upon to contribute to the final suite of algorithms used to identify the best audience. Using Alteryx, R, Tableau and our internal machine learning infrastructure, we were able to combine decades worth of client side data with decades worth of external data and output a blended master analytic database that accounted for full promotional and transactional history with all corresponding composite data on the individuals. This symphony achieved all of the goals, and then some.

 

Macro.png

 

workflow (2).png

Describe the benefits you have achieved

The client experienced a 24% reduction in their cost to acquire a donor, they were able to reactivate a much larger than anticipated volume of lapsed donors (some were inactive for over 15 years) and they discovered an entirely new set of list sources that are delivering a cost to acquire in line with their budget requirements. Mission accomplished.

 

Since that point, we have broadened the scope of our engagement and are solving for other things such as digital fundraising, mid-level and major donors. Wouldn't have been possible to do with the same speed and precision had we not been using Alteryx.

Author: Alberto Guisande (@Aguisande), Services Director

 

Awards Category: Most Unexpected Insight - Proving teachers wrong - Apples & Oranges can be compared! (thanks to Alteryx)

  

Describe the problem you needed to solve 

Our customer is a Public Transportation company, in charge of buses going around the city of Panama. They transport more than 500K passengers a day (1/6 of the total population of the country). Almost 400 routes, with 1,400 buses going around the city all days, working 24/7, reporting position every a few seconds. The company is supporting its operation with a variety of tools, but at the time to put all data together, they realized there was no "point of contact" in the data. They have to compare apples & oranges! Really? Why does the saying exist? Because you can't! So we started trying to do the impossible!

 

BTW, the business questions are pretty simple (once you got the data!): What route was every bus in, when every transaction occurred? What is the demand of every route? and for every stop?

 

Describe the working solution

Working with Alteryx, we were able to analyze data coming from three different sources, where the only common information was some LATITUDE & LONGITUDE (taken with different equipment, so the accuracy was, at least, questionable) at some random points in time. The data was received in several files:

 

  • Routes: Contains the ID & the name of every route. Stop Points: Containing every bus stop, its LAT & LONG, and the stop name
  • Pattern Detail: Containing every route, its stops and the sequence of those stops in a route
  • Some remarks: A lot of stops are used by different routes, and there are some stops, where the bus pass through, that are not part of the specific route the bus is at

 

So far, the easy part! We managed very easily to get all this info together. Now the tricky part: There mainly two operational datasets: AVL (Every position of every bus, every n seconds, where n is an arbitrary number between 0 and what the piece of hardware wanted to use). BTW, a huge amount of data every day.

 

Transactions: transactions registered in time, in a bus. As you may infer, there are no data in common that allow us to match records beside an arbitrary range of latitude and longitude in some random time ranges. Because of how everything is reported, the bus may be passing in front a stop that is part of another route, or stopping far from the designated stop.

 

Describe the benefits you have achieved

With this solution, the company can start analyzing activity per route, demand per bus, route, stop, etc. Without Alteryx, this customer information still be looking like apples and oranges! We were able to make it sense and allow them to use it to get insights.

 

Colorful note(and some ego elevator) : 5 other vendors took the challenge. No other one could reach a glimpse of solution (of course, "no Alteryx, no gain").

 

Processpng.png

Process2.png

Process3.png

Author: Andrew Kim, Analyst (@andrewdatakim)

 

Awards Category: Name Your Own - Scaling Your Career with Alteryx

 

Describe the problem you needed to solve 

Deciding on a tool to invest your time in is a problem everyone faces in their career. Learning to blend the tools given to us in college versus what the professional world is actually using are starkly different. I have quickly discovered to have a career that has both the opportunity to start from a company from scratch and the flexibility to work in a Fortune 100 environment requires the knowledge of assets that can scale without a significant investment of time or money.  My background is in Marketing and Finance with most of my work experience in small to midsize companies where every person is required to be/do more for the company to survive.

 

Describe the working solution

I set out to find these tools 3 years ago with the understanding that information drives a business, which lead me to Gartner report. I went through trials of a dozen different options and even had contracted assistance from a developer of one of the software options. Alteryx quickly became my option of choice which greatly contributed to my  previous company's growth from $250k in annual revenue online to $12 million in 2 years. The ability to access multiple data source types, leverage Amazon MWS data and use historical competitive landscape information allowed us to create the perfect dashboards in Tableau to analyze current inventory and buying opportunities that were previously inconceivable.  I was able to save 10,000 labor hours a day in discovering new products. Prior to Alteryx being purchased the average buyer's assistant could run 200 Amazon listings per 8 hour day. After Alteryx we were retrieving over 250,000 listings per run multiple times a day (The math: 250,000/25 listings per hour=10,000 hours per run). The primary customer in this scenario were the buyers for the company. By taking all of the data processed through Alteryx and providing them with Tableau dashboards to conveniently view current and historical product information compared to the previous Excel models we were able to maximize inventory turnover and margins.

 

Describe the benefits you have achieved

Alteryx knowledge allowed me to advance to my current company and position in a Fortune 50 company where I am a Data Analyst/Programmer. I now work heavily with survey data and again Alteryx has proven an indispensable asset even with the change in scale. Its versatility has allowed all of my skills to transfer from operational data to qualitative without skipping a beat. I find Alteryx is an asset that has only increased my passion for data and I am eager to see how I can continue to scale my career with it.

Author: Qin Lee, Business Analyst

Company: MSXI

 

Awards Category: Most Unexpected Insight

 

Huge data, large file and multiple applications have been created and saved and shared in a small size of Alteryx file. And now, I can test the script/coding and find the errors. This is the good way to develop the proof of concept for our company.

 

Describe the problem you needed to solve 

We need to go through many applications to get the data and save into one location to share and view.

 

Describe the working solution

We are blending the data sources form SQL, Access Excel and Hadoop, Yes, we are leveraging many parties' data. We are developing the workflows and functions for a concept now. Yes, we are exporting to a visualization tool.

 

image002.jpg

 

image004.jpg

 

Describe the benefits you have achieved

Collected the data from many locations and saved into a small size of the Alteryx database file and created the workflow and function and developed a search engine and design the proof of concept for approval and launch. Saved time and resolved the problem and increased customer satisfaction. I would like to send my sincere thanks to Mr. Mark Frisch (@MarqueeCrew), who helped us for many days to finish this project.

DSC_0035.JPGAuthor: Erik Miller (@erik_miller), Sr Systems Engineer - Cyber Security Analytics

 

Awards Category: Most Time Saved

 

Describe the problem you needed to solve

My team's story starts from the ground level of analytics: no tools, no resources, no defined data sources. But our Information Security team had an idea: to be able to report out on all of Western Union's Agent Locations (think Kroger grocery stores, mom & pop shops, etc) and the risk they posed by not having certain security measures implemented - look at every PC/terminal they have to determine their individual risks (2.4 million when we started), their fraud history, their transaction limits, etc, etc. and risk-rate every one of those 500,000+ Locations. We completed a proof of concept and realized it was completely unsustainable, requiring over 100+ hours every month to be able to produce, what outwardly looked like, a simple report. We took that process and built it out in Alteryx. And with just a little over 2.5 hours with the tool, we took a process which dominated my time and turned it into a 5 ½ minute layout of time. What's more, we've turned this POC project and turned it into a full-fledged program and department, focused on risk analytics surrounding employee & contractor resource usage (malicious or uneducated insiders), customer web analytics (looking for hackers), and further Agent analytics.

 

Beyond our humble beginnings, there's the constant threat of data breaches, fraud, and malicious insiders in the Information Security world - it's the reality of the work we do. Having the ability to build out an strategic analytics program has been a huge step in the right direction in our industry and company & not an area which many other companies have been able to focus on, which also sets us ahead of the curve.

 

Describe the working solution

We are using Alteryx to assess several data sources - HR data sets for active/terminated employees & contractors, clickstream data from our digital assets and websites, security data from our Netezza system, fraud data, log files from our various security platforms, user behavior data from our UBA (User Behavior Analytics) system, Identity and Access Management attributes/entitlements, system infection logs, installed applications, etc., etc. As I've said in other talks, we don't have a data lake, we have an ocean.

 

We are currently exporting our data to Tableau tde files, Hadoop, and MySQL databases. In addition, we have started looking/experimenting with our Alteryx Server implementation (which I support for our company).

 

Describe the benefits you have achieved

Overall time savings is nearing 150 hours a month, so a massive savings and an ability for our team to stay incredibly lean - no additional FTEs needed to keep taking on more and more data and challenges. We've also been able to give visibility to the security implementations for all of our 500,000+ worldwide locations - something which we didn't have visibility to prior to now, and which helps us drive the business to implement security features where needed - based on logic, numbers, and fraud data, not feelings.

 

We also are able to provide insights into our user base - how are our employees using our assets, what are they doing that's lowering our security posture, how are they getting infected. We're providing insights which can help our company become more secure.

 erik_miller_workflow.png

How much time has your organization saved by using Alteryx workflows?

What has this time savings allowed you to do?

With just our first workflow, we saved over 100 hours per month - so over a full FTE of time has been taken off of my plate. Alter
yx has allowed us to now only save time each month, but keep our team incredibly lean (we only have three people, and that's all we need to churn through massive amounts of security & fraud data each month).

 

So what has this time saving allowed us to do? Many, many things.

 

First, I was promoted to Sr. Systems Engineer - Cyber Security Analytics. With that change in title, also came the opportunity to build out a strategic-focused Information Security Analytics team, focused on looking at all security data throughout the company and identifying areas where we can improve our security program and posture.

 

Second, It's allowed me time to work with other departments to build out their analytics programs and help them learn to use the Alteryx tools in their respective areas.

 

Third, it's allowed my team to work on new, expanding projects with great ease.

Author: Michael Barone, Data Scientist
Company: Paychex Inc

Awards Category: Best Use of Predictive

 

Describe the problem you needed to solve

Each month, we run two-dozen predictive models on our client base (600,000 clients). These models include various up-sell, cross-sell, retention, and credit risk models. For each model, we generally group clients into various buckets that identify how likely they are to buy a product/leave us/default on payment, etc. Getting these results into the hands of the end-users who will then make decisions is an arduous task, as there are many different end-users, and each end-user can have specific criteria they are focused on (clients in a certain zone, clients with a certain number of employees, clients in a certain industry, etc.).


Describe the working solution

I have a prototype app deployed via Alteryx Server that allows the end-user to “self-service” their modeling and client criteria needs. This is not in Production as of yet, but potentially provides great accessibility to the end-user without the need of a “go-between” (my department) to filter and distribute massive client lists.

 

Step 1: ETL

  • I have an app that runs every month after our main company data sources have been refreshed:

51.png

This results in several YXDBs that are used in the models. Not all YXDBs are used in all models. This creates a central repository for all YXDBs, from which each specific model can pull in what is needed.

  • We also make use of Calgary databases as well, for our really large data sets (billions of records).

52.png

Once all the YXDBs and CYDBs are created, we then run our models. Here is just one of our 24 models:

53.png

  • Our Data Scientists like to write raw R-code, so the R tool used before the final Output Tool at the bottom contains their code:

54.png

The individual model scores are stored in CYDB format, to make the app run fast (since the end-user will be querying against millions and millions of records). Client information is also stored in this format, for this same reason.

 

Step 2: App

  • Since the end-user will be making selections from a tree, we have to create the codes for the various trees and their branches. I want them to be able to pick through two trees – one for the model(s) they want, and one for the client attributes they want. For this app, they must choose a model, or no results will be returned. They DO NOT have to choose client attributes. If no attribute is chosen, then the entire client base will be returned. This presents a challenge in key-building, since normally an app that utilizes trees only returns values for keys that are selected. The solution is to attach keys to each client record for each attribute. My module to build the keys in such a way as I described is here (and there will be 12 different attributes from which the user can choose):

545.png

  • Here is what the client database looks like once the keys are created and appended:

56.png

  • The model keys do not have to be as complex a build as client keys, because the user is notified that if they don’t make a model selection, then no data will be returned:

57.png

  • Once the key tables are properly made, we design the app. For the model selection, there is only one key (since there is only one variable, namely, the model). This is on the far right hand side. This makes use of the very powerful and fast Calgary join (joining the key from the pick-list to the key in the model table). For the client table, since there are 12 attributes/keys, we need 12 Calgary joins. Again, this is why we put the database into Calgary format. At the very end, we simply join the clients returned to the model selected:

58.png

 

Step 3: Gallery

  • Using our private server behind our own firewall, we set up a Gallery and Studio for our apps:

59.png

  • The app can now be run, and the results can be downloaded by the end-user to CSV (I even put a link to an “at-a-glance” guide to all our models):

591.png

  • The user can select the model(s) they want, and the scores they want:

592.png

And then they can select the various client criteria:

593.png

Once done running (takes anywhere between 10 – 30 seconds), they can download their results to CSV:

594.png

 

Describe the benefits you have achieved

Not having to send out two dozen lists to the end-users, and the end users not having to wait for me to send them (can get them on their own).  More efficient and streamlined giving them a self-service tool.

Author: Slaven Sljivar, Vice President, Analytics

Company: SmartDrive Systems, Inc.

 

Awards Category: Most Time Saved

 

Describe the problem you needed to solve

SmartDrive’s Analytics Team, which is approaching its 9th year in its existence in our 12-year-old company, is focused on three areas: 1) customer-facing analytics, 2) analytics supporting the internal teams, and 3) analytics as it is embedded within our product.  To support these activities, we rely a well-developed data warehousing and business intelligence stack that includes Tableau, R, SQL Server (for relational dimensional data warehouse) and SQL Server Analysis Services cubes. 

 

Alteryx, which we first started using only 5 months ago (March 2016), fills in a gap in our ability to quickly integrate data.  Prior to Alteryx, we relied on a combination of R scrips, SQL stored procedures and SQL Server Integration Services (SSIS) jobs to develop data integration solutions.  While this approach worked for us over the years, it had several drawbacks:

  1. It was a more “code-heavy” approach than we liked. While our Analytics team is comprised of competent coders and scripters, we seek to minimize the amount of code we generate (and maintain!)
  2. It was relatively slow and labor-intensive. A project that involved data integration took much longer to complete than a project that could be completed with “curated” data that already existed in our data warehouse and/or cubes.
  3. It was not very maintainable. Once a failure occurred or an enhancement was needed, dealing with code made it more difficult to get into “flow of things” compared to dealing with visual workflows.

 

One specific example is a repetitive analysis that we call “Fuel Savings Analysis” (FSA).  The goal of this analysis is to evaluate how much fuel our customers (commercial vehicle fleets) saved from drivers operating their vehicles differently after SmartDrive’s video event recorders were installed in the vehicles.  Because video event recorders activate in response to unsafe and abrupt maneuvers, drivers tend to avoid executing such maneuvers.  These maneuvers also often lead to fuel waste.  For example, harsh braking wastes more kinetic energy than gradually coasting down and using the kinetic energy (and not fuel) to overcome the rolling friction and aerodynamic drag. 

 

We had already developed a tool that automated the FSA analysis, utilizing stored procedures, R code, custom data cubes and Tableau.  However, the tool required several manual steps and needed to be run for one customer at a time.  As the result, SmartDrive’s Account Management team had to make a request of the Analytics team whenever the analysis needed to be run, and the Analytics team needed to expend 2 to 3 hours of effort for each request.

 

In April 2016, one month after we started using Alteryx, our Marketing team asked for the analysis to be done that assessed the fuel savings for all SmartDrive customers.  They were interested in including that statistics in an upcoming momentum press release.  Of course, this was not achievable with the existing tool, so we thought we would try to implement the workflow in Alteryx.  We were ultimately successful in being able to support this request, leading to the following paragraph being included in the April 12th, 2016 press release:

 

Saved customers an average of $4,903 per vehicle per year—with annual per vehicle savings of $1,878 in collision exoneration, $1,784 in collision cost reduction, and $1,240 in fuel expense


Describe the working solution

Our Alteryx workflow solution issues several queries against the data warehouse, with the primary (and the largest) query representing fuel consumption and distance driven for each customer vehicle and for each week that the vehicle was driven. This is combined with a dataset that tracks when each customer site was installed with SmartDrive, so that baseline and treatment period data can be separated. An R script that employs a decision tree (rpart) is used to group vehicles and is embedded within the workflow. The key calculation for the expected fuel consumption in the treatment period (e.g. scenario that removes the effect of SmartDrive) is calculated in Alteryx, and the resulting dataset is published on Tableau Server. We authored a Tableau workbook that implements additional calculations (e.g. % fuel savings, $ savings, etc.) and allows our Account Management team to create visuals that can be shared directly with the customer. The Alteryx workflow is scheduled to run weekly every Tuesday. In less than 30 minutes, the workflow processes the entire customer dataset, with the bulk of the time being spent waiting for the data warehouse to generate the vehicle-week extract. The entire workflow is shown in the image below.

 

41.png

 

Describe the benefits you have achieved

In this particular example, Alteryx allowed us to completely streamline a process that was already largely automated using other tools. While we could have invested more time to fully automate the existing tool, that would have involved so much effort that we have repeatedly decided to de-prioritize that work.

 

Now that we have a fully-streamlined process, our Account Management team is able to “pull up” the Fuel Savings Analysis visualization (“report”) on their own, with up-to-date results. Also, our Marketing team is able to report on the overall actual fuel savings realized by SmartDrive customers.

 

Beyond the Analytics team no longer needing to spend time and effort on running the Fuel Savings Analyses, this new capability allows our Account Management team to more consistently present the fuel savings results to our customers, particularly those that are still piloting SmartDrive. This leads to increased revenue from improved pilot conversion and also greater customer satisfaction stemming from the knowledge that their investment in SmartDrive service is generating positive financial returns.

Author: Cesar Robles, Sales Intelligence Manager 

Company: Bavaria S.A.

 

Awards Category: Best Business ROI

 

Describe the problem you needed to solve

In September 30th 2015, a gossip widespread through whatsapp reduces our Pony Malta sales to 40% of normal levels. The social networks’ gossip that impacts a brand destroys brand equity and creates distrust in our customers. Our company executes a 1st stage plan that helps to spread the gossip in the first weeks to more customers increasing the crisis. In Colombia no brand had suffered an attack like this before.

 

Describe the working solution

The Alteryx solution was develop to design and decision tree that define which customers has an relevant impact in sales volume in 5 groups that allows define differentiated protocols to recover our sales in a healthy way. These 5 groups were:

 

Citizens: Actual Customers without any impact related to social network crisis.
Refugees: Customers that reduce significantly (<50%) his rate of sales related to social network crisis.
Deportees: Customers that didn’t bought our brand related to social network crisis.
Pilgrims: Customers with doubts about our products related to social network crisis.
Aliens: New customers without any impact related to social network crisis.

 

Our gap in crisis was 180k PoS (Point of Sales) impacting 92 KHl (Kilo-hecto-liters)

 

This workflow runs monthly and uses multiple sources of information in SQL server related to Customer properties and historic sales levels. We report some results in Excel and Java applications to define our performance in recovery actions. Actually we are migrating to in database process to optimize the algorithm performance and use Tableau to manage our visualization process.

 

11.png

Figure 1. Decision Tree description

 

12.png

Figure 2. 1st Quarter Deportees results

 

13.png

Figure 3. 1st Quarter Refugees results

 

14.png

Figure 4. 1st Quarter Citizens results

 

15.png

Figure 5. Numerical Distribution Initial and End State

 

16.png

Figure 6. Blending Workflow

 

17.png

Figure 7. Decision Tree workflow

 

18.png

Figure 8. Hierarchy and Priority workflow

 

Describe the benefits you have achieved

The project defines a new way to customer segmentation in our company. We use the same algorithm to define not only crisis contingence, also we used to brand expansion and price control process including geographical variables and external info of our providers (Nielsen, YanHass, Millward Brown).

 

The solution had not been implemented before Alteryx. An estimated time saving show us that initial state needs 2 or 3 weeks to develop compared with 4 or 5 days that we used in Alteryx (We just used it 1 month ago in the firs solution). Right now our response time is less than 2 days in similar solutions.

 

In Business terms, we achieve to recover 100k PoS (approximately 25% of all Colombia Market) and increase our sales in 75% of normal levels in the first 3 months. In August 2016, we recover our normal levels of sales with the trade marketing actions focused support by Alteryx workflow.

Author: Brett Herman ( @brett_hermann ) , Project Manager, Data Visualization In-2CRev-28px-R.png

Company: Cineplex

 

Cineplex Inc. (“Cineplex”) is one of Canada’s leading entertainment companies and operates one of the most modern and fully digitized motion picture theatre circuits in the world. A top-tier Canadian brand, Cineplex operates numerous businesses including theatrical exhibition, food service, amusement gaming, alternative programming (Cineplex Events), Cineplex Media, Cineplex Digital Media, and the online sale of home entertainment content through CineplexStore.com and on apps embedded in various electronic devices. Cineplex is also a joint venture partner in SCENE – Canada’s largest entertainment loyalty program. 

 

Awards Category: Most Time Saved

 

Describe the problem you needed to solve 

Incremental/Uplift Modelling is a popular method of evaluating the success of business initiatives at Cineplex. Its effectiveness at measuring the change in consumer behavior over time creates a high demand to produce this kind of analysis for various departments in the organization. Due to the large amount of requests we receive, the ‘Incremental Lift Model’ was developed to take in user-defined inputs, and output the results within a short period of time.

 

Describe the working solution

Our solution works through a four step process. The first step is for the client to populate the ‘study input form’ in order to define their study parameters and the type of study they want to run.

 

Visual 1: Study Input Form

Alteryx Analytics Excellence Awards 2016 2H - bhermann - Visual 1.jpg

 

The second step is to update/materialize our loyalty data that’s inputted into the model (yxdb format). We do this so that the model doesn’t put stress on our SQL Server databases, and to increase the model’s performance.

 

Visual 2: Update/Materialize Alteryx Input Data

Alteryx Analytics Excellence Awards 2016 2H - bhermann - Visual 2.jpg

 

The third step is the core of the incremental lift modelling. A macro processes one study at a time by pointing to the user defined inputs made in the first step.

 

Visual 3: Study Numbers are selected and passed through the incremental lift macro, and saves the output to SQL.

Alteryx Analytics Excellence Awards 2016 2H - bhermann - Visual 3.jpg

 

The data will then be passed through one of several macros depending on the study type, and filtered down based on the inputs defined by the user in the study input form. All data sources are joined together and lift calculations are made, which are then outputted into a master SQL Table ready to be visualized.

 

Visual 4: Incremental Lift Modelling based on study type selected.

Alteryx Analytics Excellence Awards 2016 2H - bhermann - Visual 4.jpg

 

The results are visualized using a Tableau Dashboard in order to share and communicate the results of the study back to the business clients.

 

Visual 5: Tableau Dashboard to explain to the business how the incremental lift model makes its calculations.

Alteryx Analytics Excellence Awards 2016 2H - bhermann - Visual 5.jpg

 

Alteryx Analytics Excellence Awards 2016 2H -bhermann - Visual 6.jpg

 

 

Describe the benefits you have achieved

The overarching goal of this project was twofold; to minimize the amount of work required to process business requests while maximizing the output generated, and to develop a means of delivering the results in a consistent manner. Both of these goals contribute greatly to our ROI by virtually eliminating all time spent executing requests that come in, and by minimizing time spent meeting with business users to explain how the incremental lift model works and how to interpret the results.

 

Suzanne.pngAuthor: Suzanne McCartin (@SMCCARTI) , Sr. Ops Reporting Analyst

Company: Nike, Inc.

 

Awards Category: Name Your Own - Get Back In Time

 

Describe the problem you needed to solve 

My two my personal favorite Nike values are 'Simplify and Go' and 'Evolve Immediately'!    In Nike Apparel Global Product Creation Operations.  Our immediate need was to replace a critical and core data set on a tight timeline.  Making sure our product creation centers didn't lose buy tracking visibility.     Buy readiness is the measure and metric for garment commercialization.  Do we have everything we need to purchase?   This was just the beginning...

 

Describe the working solution

The buy ready metric process was implemented using a combination of tools and the first step was to replace the one data source, adding Alteryx to the tool mix.  The build process was then reconstructed and migrated to Altetyx using blending and in-database tools.  Going from about a 5 hour process to 1 hour.

 

The next follow up solution was to upgrade the report generation processes.  The first solution was one process for each output, and each one had its own data collection process.  Each of these solutions was moved to one workflow using the same data collection process.   Allowing me to enforce Nike's single version of the truth mantra!  This solution  has all kinds of data cleaning , mapping, and shaping.

 

Describe the benefits you have achieved

The first round benefit was getting the upgrade done and we did so with improved accuracy and data visibility.    The real benefit was to allow the process to get us back to the future and we are lined up to better collaborate with IT and move to Tableau and other new platforms!

Author: Michael Barone, Data Scientist

Company: Paychex Inc.

 

Awards Category: Most Time Saved

 

We currently have more than two dozen predictive models, pulling data of all shapes and sizes from many different sources.  Total processing time for a round of scoring takes 4 hours.  Before Alteryx, we had a dozen models, and processing took around 96 hours.  That's a 2x increase in our model portfolio, but a 24x decrease in processing time.

 

Describe the problem you needed to solve 

Our Predictive Modeling group, which began in the early-to-mid 2000s, had grown from one person to four people by summer 2012.  I was one of those four.  Our Portfolio had grown from one model, to more than a dozen.  We were what you might call a self-starting group.  While we had the blessing of upper Management, we were small and independent, doing all research, development, and analysis ourselves.  We started with using the typical every day Enterprise solutions for software.  While those solutions worked well for a few years, by the time we were up to a dozen models, we had outgrown those solutions.  A typical round of "model scoring" which we did at the beginning of ever y month, took about two-and-a-half weeks, and ninety-five percent of that was system processing time which consisted of cleansing, blending, and transforming the data from varying sources.

 

Describe the working solution

We blend data from our internal databases - everything from Excel and Access, to Oracle, SQL Server, and Netezza.  Several models include data from 3rd party sources such as D&B, and the Experian CAPE file we get with out Alteryx data package.

 

Describe the benefits you have achieved

We recently have taken on projects that require us processing and analyzing billions of records of data.  Thanks to Alteryx and more specifically the Calgary format, most of our time is spent analyzing the data, not pulling, blending, and processing.  This leads to faster delivery time of results, and faster business insight.

Author: Wayne Franklin, Student Experience Evaluation Officer

Company: Charles Darwin University

 

Awards Category: Most Time Saved

 

The time saved mainly effects my workload; this in turn allows me to work on other projects for the department which helps the overall organisation. Being a smaller organisation our resources are limited so any time saved makes a significant difference to our overall output. Using Alteryx has quite often saved days of manual work and it significantly reduces the risk of errors.

 

Describe the problem you needed to solve 

The issue we faced was how best to amalgamate multiple data tables into three new unique excel files to be used by a 3rd party survey tool - Blue eXplorance. While this doesn't sound too difficult, it becomes very time consuming when there are thousands of rows of data in each data source. Being a smaller educational institutional I am at present the only person that works with all the setting up, running and reporting of all the surveys within the university; spending a day or two stuck on setting up one survey can have a detrimental effect on other projects.

 

Describe the working solution

The old way of doing things: Download each of the data sources which included the full student and unit information for a given semester. This was followed by a series of pivot tables, copy pasting, creating new fields, making things more meaningful (i.e. change 'M' to Male - not much but supervisors like it better that way). Once all that was done I would eventually end up with clean unit, student and relationship files that are set up to be used for 3rd party survey software. This doesn't sound like much but is quite time consuming. I got pretty good at excel formulas which helped cut the time down a little, but still took a day messing around in excel to get the final product. The new way to do things: click run on the Alteryx app I made, wait a minute, done! The app I created allows me to select the files to upload and where to save the output files at the end.

 

Describe the benefits you have achieved

What started as a solid day or two work is now reduced to a minute wait time as the Alteryx app is running. This frees me up to continue work on other projects I am working on and be a more productive member of our team.

Author: Jeffrey Jones (@JeffreyJones), Chief Analytics Officer  In-2CRev-28px-R.png

Company: Bristlecone Holdings

 

Awards Category:  Name Your Own - Most Entertaining (but Super-Practical) Use of Alteryx

 

Describe the problem you needed to solve 

Our marketing department needed a working Sex Machine, but that sort of thing was strictly prohibited in our technology stack.

 

Describe the working solution

Analytics built a functional Sex Machine! Let me explain...

 

Because our business involves consumer lending, we absolutely cannot -- no way no how -- make any kind of decisioning based on sex or gender. Regulators don't want you discriminating based on that and so we don't even bother to ask about it in our online application nor do we store anything related to sex in our database. Sex is taboo when it comes to the Equal Opportunity Credit Act. But the problem was that the marketing department needed better insight into our customer demographics so that they could adjust their campaigns and the messaging on our website, videos, etc., based on actual data instead of gut instinct.

 

Well, it turns out the Census Bureau publishes awesome (and clean) data on baby names and their sex. So we made a quick little workflow to import and join 134 years of births in the U.S. resulting in over 1.8 million different name/sex/year combinations. We counted the occurrences, looked at the ratio of M to F births for each and made some (fairly good) generalizations about whether a name was more likely a "Male" name or "Female" name. Some were pretty obvious, like "John." Others were less obvious, like "Jo." And some were totally indeterminate, like "Jahni."

 

Then we joined this brand new data set to an export of our 200k customer applications and were able to determine the sex of around 90% our applicants fairly reliably, another 7% with less reliability, and only 3% as completely unknown. The best thing about it is that we were able to answer these questions completely outside our lending technology stack in a manner disconnected from our decisioning engine so as to maintain legal compliance. We also didn't have to waste any money or time on conducting additional customer surveys.

 

This was literally something that was conceived in the middle of the night and had been born into production before lunch on the following day. (bow-chicka-bow-bow) Doing this wouldn't have been just impossible before Alteryx, it would have been LAUGHABLY IMPOSSIBLE. Especially given the size of the third-party data we needed to leverage and the nature of our tech stack and the way regulation works in consumer lending.

 

Describe the benefits you have achieved

It sounds silly, but our organization did realize tangible benefit from doing this. Before, we had no idea about a critical demographic component for our customers. It's impossible to look a bank of nearly 200k names across four totally unrelated industry verticals and conclude with any kind of confidence sex-related trends. Now we can understand sex-related trends in the furniture, bridal, pet, and auto industries. We can link it to the products they're actually getting and tweak the messaging on our website accordingly. And what's more, we're able to do all this in real-time going forward without wasting any of our DBAs' time or distracting our legal department. This probably saved us a hundred man-hours or more given all the parties that would have needed to get involved to answer this simple demographic question.

 

We should probably tidy up this workflow and the .yxdb because it might be useful for other companies who want to get a full demographic breakdown but don't have any pre-existing information on customer sex. If anybody wants to know the total number of people born with every name for the last 134 years and needs the M:F occurrence ratio for each, holler at me.

Author: Mandy Luo, Chief Actuary and Head of Data Analytics

Company: ReMark International

 

Awards Category: Best Use of Predictive

As a trained Statistician, I understand why "70% data, 30% model" is not an exaggeration. Therefore, before applying any regression models, I always make sure that input data are fully reviewed and understood. I use various data preparation tools to explore, filter, select, sample or join up data sources. I also utilize the data investigation tools to conduct or validate any statistical evaluation. Next, I would usually choose 3-5 predictive modeling candidates depending on the modeling objective and data size. I often include one machine learning methods in order to at least benchmark other models. After the modeling candidates finish running, I would select the best model based on both art (whether the coefficients look reasonable based on my understanding of the data and business) and science (statistical criteria's like the goodness of fit, P-value and cumulative lift etc.).  I am also often using the render function for model presentation and scoring/sorting  function for model validation and application.

 

Describe the problem you needed to solve 

ReMark is not only an early adopter in predictive modeling for life insurance, but also a true action taker on customer centricity by focusing on customer lifetime analytics (instead of focusing on 'buying' only). In this context, we need to 'join up' our predictive models on customer response, conversion and lapse in order to understand the most powerful predictors that drive customer activities across pre and post sales cycle. We believe the industry understand that it is insufficient to only focus on any single customer activity, but is still exploring how this can be improved through modeling and analytics, which is where we can add value.

 

Describe the working solution

Our working solution goes with the following steps:

  1. Match over one year post sales tracking data back to sales payment data and marketing data (all de-personalized)
  2. Build 3 predictive models: sale(whether the purchase is agreed or not), conversion (whether the first premium bill is paid or not), 1 year persistency (whether lapse happened at month 13 or not).
  3. Compare model results by key customer segments and profiles
  4. Expert to visualization tool (e.g. Tableau) to present results
  5. Model use test: scoring overlay and optimization strategy

 

Describe the benefits you have achieved

  • We could create customer segments' not just based on tendency to 'buy', but also tendency to 'pay' and 'stay'.
  • We could further demonstrate ReMark's analytics and modeling capabilities covering the whole customer lifetime value chain without missing out

Author: Sintyadi Thong ( @MizunashiSinayu ), Pre-Sales Consultant, Karen Kamira & Harry Yusuf

Company: Lightstream Analytics PTE Ltd.

 

LightStream Analytics focuses on performance management, big data, advanced analytics, and innovative visualization through cloud SaaS applications, mobile, and traditional on-site systems. LightStream Analytics is well-positioned to deliver the most advanced products and services by capitalizing on its significant regional presence in Singapore and Indonesia. The combined offices have over 60 employees with deep technical and senior business experience. The company leverages our existing technical support and R&D centers in Indonesia and China to develop solutions which disrupt customary methods of data analysis and give clients access to revolutionary tools for understanding their data.  LightStream Analytics has partnered with more than 100 multinational and local clients to integrate, structure, analyze, and visualize information to measure their business performance and drive enterprise value growth.

 

Awards Category: Most Time Saved

  

Describe the problem you needed to solve 

 

One of our clients tried to implement one of the most Business Intelligence solution to help them grow their business through another company (we can pretty much say our competitor). However, there is one thing which hinders their development of the BI. When usually most companies want to see the date of sales (on which date their agents perform sales), this company would like to see the other way around, they would like to see ‘on which dates their agents do not perform sales activity’. For them this is very important. The BI developers hit a dead-end on this thing, and therefore I came with Alteryx.

 

Describe the working solution

 The BI I previously mentioned is QlikView. Well Qlik can do it, and I can guarantee. But it involves heavy scripting and logic. With heavy scripting it will also mean it requires heavy resources to perform the run (will only be visible when running with low RAM). Alteryx on the other hand can do this easily using drag-and-drop and repeatable workflow, so I feed Alteryx with the actual sales data, perform several left joins, filter, and unique. Alteryx requires no scripting, and to be honest I am not even an IT guy, I know nothing about SQL and programming, but I can create this workflow easily. So we proposed to have Alteryx prepare and blend the data before feeding it to QlikView, therefore it will help to make the data visible before feeding it to QlikView and lessens the burden on QlikView. While the client has not yet confirmed whether they will get Alteryx or not, it is really satisfying and rewarding to solve this problem easily while others had hardships in getting this result.

 

Describe the benefits you have achieved

While I created the workflow in only an hour vs their 2 weeks development for this one case (and in which they failed after 2 weeks), this shows how much of a time savings the client would get if they developed QlikView alongside with Alteryx. Alteryx will help the customers to get results faster and perform an advanced ETL which might be hard to do in traditional SQL language.

Author: Andrew Simnick, Head of Strategy

Company: Art Institute of Chicago

 

Awards Category: Best 'Alteryx for Good' Story

 

The Art Institute of Chicago is one of the world's greatest art museums, staying true to our founding mission to collect, preserve, and interpret works of art of the highest quality from across the globe for the inspiration and education of our audiences. Today we face new competition for visitor attention, a continued responsibility to expand our audiences, and an increasingly-challenging economic environment.  Alteryx has allowed us to quickly overcome our data and resource constraints, develop a deeper understanding of our local audiences, and strike a balance between mission- and revenue-driven activities to continue to deliver on our mission for Chicago.

 

Describe the problem you needed to solve 

We, as do other museums, face the challenges of growing our audience while  maintaining a strong financial foundation. Our strategy to navigate this has been to increase visit frequency from our core visitor segments in the near term and use this increase to further expand outreach to new local audiences. However, our challenges to achieving this have been three-fold. First, visitor segmentation in the arts and culture space is a relatively recent concept, and general segmentation schema are not always applicable to Chicago at a granular level. Second, we have very useful data but in inconsistent formats, ranging from handwritten notes and Excel documents to normalized but disconnected databases. Third, we are resource-constrained as an institution and cannot dedicate large amounts of time or money towards dedicated analytics or external consulting.

 

Describe the working solution

First, we built a database describing the Chicago CBSA at the census block group level, providing the nuance necessary for a city where demographics change block-to-block and limit the utility of ZIP code analysis. Alteryx allowed us to get to this new additional level of detail and make our analysis relevant to Chicago. Using the Allocate Input and Calgary Join, we applied information from the US Census as well as Experian data sets. We utilized basic data such as population, income, and education, as well as proprietary Experian segments such as Mosaic groups and ISPSA (Index of Social Position in Small Areas) to describe these census blocks.

 

Second, we brought together our disparate visitor data into a blendable format. Some of our datasets are well defined, such as our membership CRM which resides in a relational database on MSSQL Server, whereas others are more ad hoc, such as our Family Pass users, which are transcribed from pen and paper into an Excel document. The Join tools in Alteryx provided a simple way to bring these data together without commanding significant time from our small analytics team.

 

Third, each of these datasets was CASS Encoded and geocoded using the US Geocoder tool, providing us a spatial object. We then utilized the Spatial Match tool to find the intersection of these objects with our universe of Chicagoland Block Groups. Each of these distinct streams were then normalized and combined to the block group aggregation level resulting in our final dataset. We also utilized a shared public custom macro which allowed us to convert these block groups into polygons for visualization in Tableau.

 

Finally, we utilized heatmaps and scatterplots to identify which proprietary Experian segments correlate with our different offerings. This informed our choice of variables for our final Decision Tree tool analysis, which identified prime target block groups associated with our different offerings. These bespoke segments created via machine learning were more applicable to our own audiences and required a fraction of the time and cost of other segmentation methods.

 

Describe the benefits you have achieved

This approach has given us a framework and the supporting intelligence from which to make institutional decisions surrounding visitor outreach and programming, allowing us to focus our resources on actions which we believe will have the greatest impact towards increased participation, attendance, and/or revenue. For example, we can now tailor membership messaging more effectively and quantify the effects on repeat visitation. We also can identify gaps in our geographic coverage of Chicagoland and test different outreach efforts to engage new audiences. Most importantly, we can unify our approach to audience development across departments using a common baseline and methodology. These combined efforts enabled by Alteryx will help us to build our audiences and fulfill our civic responsibilities well into the future.

Author: Francisco Aristiguieta, Audit Specialist

 

Awards Category: Name Your Own - Best Engagement From Management

 

Describe the problem you needed to solve 

With operations in all time-zones and more than 10,000 people, my company needed an effective way to ensure we don't have rouge employees exposing us to corruption.

 

Before our Alteryx tool, we had a very complete compliance program focused on prevention; but we did not had a viable method to verify the mandates were understood and followed across the globe.

 

Describe the working solution

Our plan was to every month inspect every payment the company had done for signs of potential problems. We would do this by searching each invoice line for keywords that could represent problems.

 

The plan was simple, although the implementation would have been an enormous problem if we had not had Alteryx.  Here are a few of the (multiple) humps Alteryx helped us address:

 

1. Payment information was broken in multiple tables. Even if we would be working with Oracle data, our IT department insisted that we worked with off-line copies of the tables instead of connecting directly. This made our data source a series of multiple monthly csv tables, where the tables had no meaning on their own.

 

>> Importing all files in a folder, and using "Unique", "Filter", "Select" and "Join"; allowed me to conquest this first challenge.

 

2. I used "find replace" to do the keyword searches; which was a great step forward. Sadly, in many cases our chosen "keywords" were part of innocent words, which caused a plague of false positives for follow-up. i.e. the word "magenta" would be caught when we searched for "agent". 

 

>> Using "Formula" to set-up some "If-Then-Else statements", and carefully using "and" to set-up my conditions, I was able to safe list some of these innocent words and get rid of a large portion of these false positives.

 

3. Because the outputs of each run is stored separately, my last big challenge was making sure I didn't report/investigate the same transactions month after month as we re-ran the tests.

 

>> Solving this was easy through a collection of file imports, "union", and "join" to compare the current results to the recent past (keeping only new hits) in my analysis.

 

Francisco_FCPATEsts.jpeg 

Describe the benefits you have achieved

Even if (after follow-up) the tests have not found any real problems, we are very happy to finally have peace of mind regarding how our employees are behaving across the world. This test was a great way to demonstrate the value of analytics to the more traditional pockets of our company, and its results have been greatly celebrated, giving me and my team some great exposure to the highest levels of my organization. Here are a few quotes from our clients:

 

  • "This is another SUCCESS for the Data Analytics initiative.  There is NO WAY we would have ever even known this was an issue without this capability "
  • "I believe that this proactive approach is clearly one of the most significant advances in early detection techniques that (the team) has implemented in quite a while"
  • "The mere fact that the word will get out that we have tools like this to potentially catch such payments should be a powerful deterrent"
  • "Our analytics practices have changed the way we (work) increasing our effectiveness and efficiency"
  • "I am looking forward  to work on another (analytics) initiative with (the team)"