Case study: GAP Analysis & Parts Potential Forecast for Automotive Giant

About the Client

The client is India’s leading manufacturer of commercial vehicles. They design, manufacture & sell a range of commercial vehicles that cater to the growing demands of Indian customers.

Business Context

The client was looking for gap analysis of spare parts consumption with various dimensions like region, segments, models. With regards to spare parts the client had the need to predict demand by region and vehicle models taking into consideration business rules, historical patterns, vehicle sales, vehicle & spare failure probabilities.

BRIDGEi2i Solution

BRIDGEi2i partnered with the client to build a front end tool for planners to get complete visibility about parts performance and dealer performance on 8765 parts leading to increase in operational effectiveness. During this engagement BRIDGEi2i also developed a forecasting model which provides a full portfolio view of parts at an overall level with an ability to drill down to the most granular level.

  • The Data Experts at BRIDGEi2i rolled up data to monthly and part level.
  • Master data creation was done by data experts.
  • Data Experts transformed variables (log, sqrt, box-cox transformation etc.)
  • The Data Engineers calculated the mean time between repairs, part failure rate, and average distance traveled between repairs.

The Data Engineers carried out inventory classification based on Pareto principle and carried out Criticality classification based on part usage. BRIDGEi2i AI labs created algorithms for demand classification and forecasting (Univariate & Probabilistic). This group of classification was based on a six month performance and was finally converted into a Champion Model.

BRIDGEi2i’s AI Labs and consulting team deployed the Demand Planning Watch Tower to provide complete visibility of GAP analysis with management view, operational view, dealer view, and critical parts view. The solution also had an integrated Optimizer to predict spare parts demand by region and vehicle models.

Business Impact

Visibility across the dealer network

0
%
Increase in Overall Accuracy
0
%
Increase in Accuracy for Highly Critical Parts