Driving with Data: Modeling and Forecasting Vehicle Fleet Maintenance in Detroit

TL;DR

This paper analyzes Detroit's vehicle fleet data from 2010-2017 using advanced data mining and modeling techniques to uncover patterns, sequences, and predict maintenance needs, aiding municipal fleet management.

Contribution

It introduces the application of tensor decomposition, differential sequence mining, and LSTM models to municipal vehicle maintenance data, revealing complex patterns and enabling predictions.

Findings

Identified unique temporal maintenance patterns.

Discovered statistically significant maintenance sequences.

Demonstrated predictive capability of LSTM models.

Abstract

The City of Detroit maintains an active fleet of over 2500 vehicles, spending an annual average of over \$5 million on new vehicle purchases and over \$7.7 million on maintaining this fleet. Understanding the existence of patterns and trends in this data could be useful to a variety of stakeholders, particularly as Detroit emerges from Chapter 9 bankruptcy, but the patterns in such data are often complex and multivariate and the city lacks dedicated resources for detailed analysis of this data. This work, a data collaboration between the Michigan Data Science Team (http://midas.umich.edu/mdst) and the City of Detroit's Operations and Infrastructure Group, seeks to address this unmet need by analyzing data from the City of Detroit's entire vehicle fleet from 2010-2017. We utilize tensor decomposition techniques to discover and visualize unique temporal patterns in vehicle maintenance; apply differential sequence mining to demonstrate the existence of common and statistically unique maintenance sequences by vehicle make and model; and, after showing these time-dependencies in the dataset, demonstrate an application of a predictive Long Short Term Memory (LSTM) neural network model to predict maintenance sequences. Our analysis shows both the complexities of municipal vehicle fleet data and useful techniques for mining and modeling such data.