Retailers stick around while others quit shopping at their store and is critical to marketing success and long-term brand viability. TechVantage has its own reusable framework helps to detect the specific shoppers who are fading away; evaluate your current customer base and estimate their value into the future; leverage Loyalty programs. This enables the business to allocate appropriate budgets for acquisition and retention.
The client had issues with availability and profitability of food products in some of their stores.
The Forecast Inventory planners were not making data driven decisions but using expert judgment.
The client approached us to refine the forecast model so as to improve forecast accuracy.
A driver model was implemented to understand what factors drive forecast error in the system post which focused initiatives were planned and implemented across improving Seasonality patterns (Holt-Winters Model).
Improving Day of Week profiles (Modeled prior performance data)
Planning for Non-Seasonal Weather changes
Rule-Based Approach Planning for Promotions
Regression Modeling of Price Elasticity
A Spot fire Dashboard was designed and dedicated for reviewing the forecast
Accuracy for the past weeks which also highlights the defaulter in terms of worst forecast across Store Types and Products.
Better Understanding of Forecast Accuracy and its levers enabled the FIP's to make more informed decisions whenever necessary and reduced unnecessary interaction with the Forecasting and Ordering System.
Implementation of the above-mentioned initiatives led to a business benefit of ~£ 2.2 M profit and an improvement in availability from 92 % to 94% along with a reduction of 0.5% waste from 6.5% to 6% for the financial year.
Client wanted to develop a early attrition indicator for their customer base so that targeted campaigns can be designed with customer retention standpoint.
Exhaustive Brainstorming was performed to chalk likely behaviors which customers would showcase before attrition which were validated using bivariate testing.
History of Customer’s Relationship with the Client like loyalty behavior, purchasing patterns, Interaction with customer care, store visits, Payment Patterns were found to be influencing customer’s decision to attrite.
Logistic Regression Model was built for customer base snapshot as of 2 years back keeping the attrition flag as the dependent and the earlier mentioned factors as Independent factors.
The accuracy of the model was assessed by checking the model results against the 30% customer base (Control Group)
~13%(~1.5M Customers) of the existing customer base was found to be likely attrition candidates Upon deep dive analysis, the effect of attrition was found to be prominent in the urban areas especially New York, California, San Francisco etc. Marketing Team was given the responsibility to design targeted campaigns to retain these customers
An Omni channel retailer based in Long Island partnered with a MSO from North East US. With the help of third-party data providers, the retailer identified their most valuable customers from the MSO subscriber base. (To identify similar customers for targeted marketing)
Demographic data provided by third party and viewership data from the MSO were used as primary attributes.
Feature Engineering to create meaningful attributes From the viewership information available. This included considering the network affinity, day of week affinity, daypart affinity so on and so forth.
Multiple classification models were developed to identify similar customers along with their propensity Outcome to visit the store.
~10% of the customers(~2M Customers) similar to existing ones were identified
Upon deep dive analysis, It was observed that the look-alikes were dominated by people who are in the age group of 50 and above are from a medium to high income group and are college graduates.
Marketing Team was given the responsibility to design targeted campaigns to acquire these customers.