Gradient Boosting Application in Forecasting of Performance Indicators Values for Measuring the Efficiency of Promotions in FMCG Retail

TL;DR

This paper introduces a gradient boosting approach to forecast promotion efficiency in FMCG retail by modeling six performance indicators across product groups, aiding in promotion optimization.

Contribution

The paper presents a novel application of gradient boosting models for forecasting promotion effectiveness using multiple indicators in FMCG retail.

Findings

Models accurately predict promotion efficiency indicators.

Effective hyperparameter tuning improves forecast accuracy.

Application demonstrated on real grocery data.

Abstract

In the paper, a problem of forecasting promotion efficiency is raised. The authors propose a new approach, using the gradient boosting method for this task. Six performance indicators are introduced to capture the promotion effect. For each of them, within predefined groups of products, a model was trained. A description of using these models for forecasting and optimising promotion efficiency is provided. Data preparation and hyperparameters tuning processes are also described. The experiments were performed for three groups of products from a large grocery company.