Retail Sales Forecasting

LightGBM achieving 13.5% WAPE for 16-day forecasting across 54 stores with 56 engineered features

Technology Stack

LightGBMXGBoostStreamlitPlotlyScikit-learnPandas
ML Frameworks
Deep Learning
NLP
Deployment

ROI

$500K+ annual savings

Key Performance Indicators

Inventory Waste Reduction
15-20%
Stockout Reduction
25-30%
Labor Efficiency
10-15% improvement

Business Impact Summary

Return on Investment$500K+ annual savings
Inventory Waste Reduction15-20%
Stockout Reduction25-30%
Labor Efficiency10-15% improvement

Overview

Production-grade forecasting platform using LightGBM for Ecuadorian grocery retailer with 54 stores and 33 product families. 16-day predictions with 56 engineered features and interactive Streamlit dashboard.

Live Demo

Live Demo

Interactive Streamlit application

📊

Retail Sales Forecasting Demo

Click below to load the interactive demo

This is a live, interactive demo deployed on Streamlit Cloud. You can:

  • •Upload your own data for predictions
  • •Explore model performance metrics
  • •View interactive visualizations
  • •Understand model predictions with explainability

Related Projects

ECC
ROC-AUC
98.1%

E-Commerce Customer Churn Prediction

Cost-optimized machine learning with 98% ROC-AUC and 60% cost reduction through threshold optimization

CatBoostXGBoostLightGBMSMOTE+4 more
MBA
AOV Increase
20-35%

Market Basket Analytics

Association rule mining and customer segmentation with 105K+ rules generating 20-35% increase in average order value

FP-GrowthAprioriK-MeansRFM Analysis+3 more