Fuel Savings Analysis of Commercial Vehicle Fleets

[DanielleR]

Author:

Slaven Sljivar

Role:

Vice President, Analytics

Company:

SmartDrive Systems, Inc.

Fuel Savings Analysis of Commercial Vehicle Fleets

Originally Published: 2016 Excellence Awards Entry 

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 12^th, 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.

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.