Engine Works
Under the hood of Alteryx: tips, tricks and how-tos.
The Fall 2015 Alteryx / UCONN MSBAPM Program Data Challenge - the second of its kind - has officially wrapped! Congratulations to all the teams that submitted projects. The top 6 teams presented their projects to a panel of judges in late October. If you would like to know more about the challengers, click their name to be taken to their LinkedIn profile. Without further ado, the top finishing teams...
First Place: Team Lift
Predicting Medication Adherence
Suresh Shanmugam (@sureshs), Prasanth Regupathy (@rcprasanth), Balasubramanian Janakarajan, and Sakthivel Sabapathy (@sakthivel230590) write:
Medication adherence is a growing public health concern in the US. It is the extent to which patients are taking medications as prescribed by their healthcare providers. Simply put, are patients eating their pills on time? We looked at patient data from Medicare part D program released by Centers for Medicare & Medicaid services. We built a prediction model to ascertain whether a patient would be adherent based on a variety of social, economic and behavioral aspects.
As part of their project the team created the following Alteryx app:
Second Place: Team Story Tellers
Hartford Crime Analysis
Ashwin Chadaga (@achadaga) and Pooja Sankhe (@poojasankhe) write:
We chose to address the issue of misinformation with the general public when it comes to the crime and its patterns in the Hartford region. Dataset which we chose for this is from the publicly available Police Incidents registered in Hartford area from 2005 till date with the time stamp. Pattern of the crime can be analyzed like e.g. Robbery incidents mainly happen during holiday season. Using the API we built a live tableau dashboard and also forecasted the drug offenses as per neighborhood.
As part of their project the team created the following Tableau dashboard:
Third Place: Team Altima
KBB-like Reference Pricing System for Rent
Hao Zhu and Yingqi Yang write:
In our project, we designed a KBB-like Reference Pricing System for rent. It was based on the K Nearest Neighbors (KNN) Regression Model, which we developed in Alteryx Designer using R script, and some other machine learning methods. We also employed techniques such as text mining and clustering. Our end product could be integrated with online apt./room/house etc. rental listings to provide people looking for rental housing with a reference point for rent negotiation.
You can find Team Altima's project attached to this post.
Thanks to all those in the Alteryx community that helped the challengers throughout the competition. Special thanks to @MarqueeCrew who went above and beyond!
