Case studies

Two forecasting case studies: demand for slow-moving spare parts on an industry client project, and a comparison of forecasting models across two book sales datasets.

Employer Project · Intermittent Demand · Cambridge

Collision Parts Demand Forecasting

An employer project forecasting slow-moving spare parts, then generalised across all four demand classes and tested on two public datasets. Why the accuracy figures mislead, and where a forecast stops being worth running.

Croston / SBA / TSB Per-SKU Selection Segmentation LightGBM
Read case study →
Time Series · Forecasting · Machine Learning

Book Sales Forecasting

Compared ARIMA, SARIMA, XGBoost, LSTM and hybrid models to forecast book demand across two datasets.

ARIMA SARIMA XGBoost LSTM
Read case study →