shreyamalogi/Industrial-Demand-Forecasting-Pipeline
Architected a high-performance predictive pipeline processing 15 Million transactions. Optimized memory by 70% via custom downcasting and implemented Tweedie-LightGBM to solve zero-inflation in retail demand. Delivered a 28-day future forecast for Walmart inventory with high-precision RMSE of 2.20.
This pipeline helps retail operations and inventory managers predict future demand for products. It takes raw sales transaction data, along with calendar and pricing information, and generates a 28-day forward-looking sales forecast. You would use this if you manage inventory or supply chains for large retail operations and need accurate predictions to optimize stock levels and logistics.
Use this if you need to transform millions of retail transaction records into precise, future-facing demand forecasts for inventory and supply chain optimization.
Not ideal if your demand forecasting needs are for a small business or do not involve processing extremely large datasets with complex retail-specific patterns.
Stars
14
Forks
—
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 03, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/shreyamalogi/Industrial-Demand-Forecasting-Pipeline"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
samirsaci/ml-forecast-features-eng
Machine Learning for Retail Sales Forecasting — Features Engineering
georgeguimaraes/soothsayer
Elixir library for time series forecasting, inspired by Facebook's Prophet and NeuralProphet
Pradnya1208/Time-series-forecasting-using-Deep-Learning
The goal of this notebook is to implement and compare different approaches to predict ...
AstraZeneca/judgyprophet
Forecasting for knowable future events using Bayesian informative priors (forecasting with...
DSkapinakis/sales-time-series-forecasting-ml-models
Sales Time Series Forecasting using Machine Learning Techniques (Random Forest, XGBoost, Stacked...