South East Asia-based large automobile spare parts and components manufacturer.
The client wanted to increase the accuracy of its short-term sales forecasts through the use of advanced predictive analytics. As a first step in the procurement process, the client had to prepare quotes for new customers who were looking to purchase components. However, the client was not able to determine whether the quote would be accepted or rejected.
SG Analytics created a quote prescription system that would predict if a given quote would be accepted or rejected by the customer. Additionally, SG Analytics built a model that, if a quote would not get accepted, suggested parameters changes, which would increase the likelihood of selection.
SG Analytics' team used random forest algorithm to predict whether a generated quote would be selected or not.
If a quote does not get accepted, the team tweaked parameters such as the discount, warranty, and delivery time using GLM (discount & delivery time), CART (decision trees), warranty (number of services in warranty), and competitor pricing based on the type of customer.
Our team used cross-validation to avoid overfitting.
We used the K-means clustering algorithm to determine customer type and divide them into eight clusters.
We wrote back the results into SQL to create data visualization in Qlikview, and also used them in model retraining.
Created a model that could predict the outcome of a quote with 86% accuracy.
Increased win rate by 23% and reduced the time of deal closure.