Problem Use Case
A leading Transportation/Logistics company, partnered with Canopus to address the below challenges.
- Route Optimization.
- Reduce fuel consumption.
- Avoid Accidents.
- Avoid Traffic.
- Time Saving.
Today’s fleets consist of high end systems such as automated gearbox, cruise control, etc. which generates a lot of data. This data can be utilized to measure the performance of the fleet and the driver. Since, big data has such
large potential if handled and analyzed in the right way, revealing information to support decision making in an organization. Canopus utilized and analyzed the organization’s fleet data in order to generate the best insights
which potentially helped the company in huge cost savings.
- We found the patterns from usage of fleets and linked the involved parameters to fuel consumption. By using Factor Analysis and Principal Component Analysis the fleets are first clustered using k-means and Hierarchical Clustering which shows groups of fleets where the importance of the properties varies.
- The importance for fuel consumption in the clusters is explored using model estimation. A comparison of Principal Component Regression (pcr) and the two regularization techniques Lasso and Elastic Net is made.
- Traffic Prediction- We calculated the statistical measures of nonlinearity and complexity for multiple datasets and correlated those to the performances of multiple models SARIMA, SVR and k nearest neighbor (k-NN). Based on this, useful insights are revealed pertaining to parameter setting and model selection based on the data diagnosis results.
- Traffic Accident Analysis- We used modularity-optimizing community detection to cluster the dataset, and for each cluster, the association rule algorithm is applied to yield insight into traffic accident hotspots and incident clearance time. We integrated the data “width” decreasing step (variable selection) and model development step for real-time traffic accident risk prediction. For this, a novel variable selection method based on the Frequent Pattern tree (FP tree) algorithm is proposed and tested, before applying Bayesian networks and the k-NN algorithms.
- By using data analysis techniques, such as dimensionality reduction, clustering and model estimation, and combining them in an overall process of multiple steps, a way of differentiating groups of fleets was derived.
- Drivers were able to change the route by getting an alert from the real-time traffic prediction system which resulted in huge time savings.
- Drivers were able to avoid many crucial accidents.
- Fuel savings alone are estimated to be more than twenty five thousand dollars per month.