Objective
A top retailer wanted to identify opportunities to increase profitability across categories without any adverse impact on revenue. The goal was to develop a recommendation engine to suggest optimal price points for each SKU factoring in demand price elasticity relationships, vendor side constraints, macro-economic conditions, competitor pricing, etc.
Our Solution
- Our price optimization module used historical transaction data to derive a price-demand relationship for each item using curve fitting and deep learning techniques.
- The optimal price is recommended (using LP/MIP algorithms) at which revenues or margin can be maximized.
- The solution factored in cost of manufacturing and cost of freight into pricing recommendations, along with competitor pricing information, seasonality, macro-economic factors, etc.
- The solution offered flexibilities for scenario analysis which significantly helps in a collaborative decision-making processes.
- The solution leveraged a self-learning approach and monitors results to continuously improve modelling accuracy.
The solution was built leveraging tcg mcube, our proprietary analytics platform that can analyse large volumes of data to drive accelerated insights. The built-in data models and data science algorithms drive velocity to value for our customers.
Project Impact and Outcomes
A data science-driven approach for pricing helped increase gross margin by 3% to 10% for various categories without any adverse impact on revenue.
