Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Improving Asset Allocation in a Fast Moving Consumer Goods B2B Company: An Interpretable Machine Learning Framework for Commercial Cooler Assignment Based on Multi-Tier Growth Targets

Renato Castro, Rodrigo Paredes, Douglas Kahn

TL;DR

This paper addresses asset allocation in FMCG B2B by predicting which clients will show sales uplift after cooler installation, framed as a multi-threshold uplift problem with targets at $10\%$, $30\%$, and $50\%$. It employs gradient-boosting models (XGBoost, LightGBM, CatBoost) with SHAP for interpretability, trained on 3,119 clients with 12 months pre/post-treatment data, and evaluated via cross-validation and holdout sets. The results indicate strong predictive performance, with LightGBM achieving the best holdout AUC at higher growth targets and CatBoost offering high precision in selective targeting; SHAP analyses reveal actionable drivers such as recency, transaction duration, and beer-volume indicators. The framework offers a scalable, ROI-focused decision support tool that balances reach, selectivity, and cost efficiency in cooler deployment, providing practical guidance for asset allocation in B2B FMCG contexts.

Abstract

In the fast-moving consumer goods (FMCG) industry, deciding where to place physical assets, such as commercial beverage coolers, can directly impact revenue growth and execution efficiency. Although churn prediction and demand forecasting have been widely studied in B2B contexts, the use of machine learning to guide asset allocation remains relatively unexplored. This paper presents a framework focused on predicting which beverage clients are most likely to deliver strong returns in volume after receiving a cooler. Using a private dataset from a well-known Central American brewing and beverage company of 3,119 B2B traditional trade channel clients that received a cooler from 2022-01 to 2024-07, and tracking 12 months of sales transactions before and after cooler installation, three growth thresholds were defined: 10%, 30% and 50% growth in sales volume year over year. The analysis compares results of machine learning models such as XGBoost, LightGBM, and CatBoost combined with SHAP for interpretable feature analysis in order to have insights into improving business operations related to cooler allocation; the results show that the best model has AUC scores of 0.857, 0.877, and 0.898 across the thresholds on the validation set. Simulations suggest that this approach can improve ROI because it better selects potential clients to grow at the expected level and increases cost savings by not assigning clients that will not grow, compared to traditional volume-based approaches with substantial business management recommendations

Improving Asset Allocation in a Fast Moving Consumer Goods B2B Company: An Interpretable Machine Learning Framework for Commercial Cooler Assignment Based on Multi-Tier Growth Targets

TL;DR

This paper addresses asset allocation in FMCG B2B by predicting which clients will show sales uplift after cooler installation, framed as a multi-threshold uplift problem with targets at , , and . It employs gradient-boosting models (XGBoost, LightGBM, CatBoost) with SHAP for interpretability, trained on 3,119 clients with 12 months pre/post-treatment data, and evaluated via cross-validation and holdout sets. The results indicate strong predictive performance, with LightGBM achieving the best holdout AUC at higher growth targets and CatBoost offering high precision in selective targeting; SHAP analyses reveal actionable drivers such as recency, transaction duration, and beer-volume indicators. The framework offers a scalable, ROI-focused decision support tool that balances reach, selectivity, and cost efficiency in cooler deployment, providing practical guidance for asset allocation in B2B FMCG contexts.

Abstract

In the fast-moving consumer goods (FMCG) industry, deciding where to place physical assets, such as commercial beverage coolers, can directly impact revenue growth and execution efficiency. Although churn prediction and demand forecasting have been widely studied in B2B contexts, the use of machine learning to guide asset allocation remains relatively unexplored. This paper presents a framework focused on predicting which beverage clients are most likely to deliver strong returns in volume after receiving a cooler. Using a private dataset from a well-known Central American brewing and beverage company of 3,119 B2B traditional trade channel clients that received a cooler from 2022-01 to 2024-07, and tracking 12 months of sales transactions before and after cooler installation, three growth thresholds were defined: 10%, 30% and 50% growth in sales volume year over year. The analysis compares results of machine learning models such as XGBoost, LightGBM, and CatBoost combined with SHAP for interpretable feature analysis in order to have insights into improving business operations related to cooler allocation; the results show that the best model has AUC scores of 0.857, 0.877, and 0.898 across the thresholds on the validation set. Simulations suggest that this approach can improve ROI because it better selects potential clients to grow at the expected level and increases cost savings by not assigning clients that will not grow, compared to traditional volume-based approaches with substantial business management recommendations

Paper Structure

This paper contains 21 sections, 1 equation, 2 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. B2B Customer Churn Prediction
  4. Interpretable Machine Learning in Business Applications
  5. Resource Allocation and Asset Optimization
  6. Problem Formulation
  7. Business Context
  8. Dataset Description
  9. Target Variable Definition
  10. Evaluation Framework
  11. Methodology
  12. Data Preprocessing and Feature Engineering
  13. Class Imbalance Handling
  14. Machine Learning Model Solutions
  15. Training and Evaluation Strategy
  16. ...and 6 more sections

Figures (2)

  • Figure 1: Monthly number of unique B2B clients receiving coolers from January 2022 to March 2025.
  • Figure 2: SHAP summary plot for 30% growth model showing top 20 features. Color indicates feature value; x-axis indicates SHAP impact on prediction.