Retail & E-commerce
Retail P&L tracks forecast accuracy directly. Miss and it becomes stockouts or waste; hit and purchasing, staffing and logistics all get lighter. What matters is forecasting many fine-grained series, per SKU and per store, quickly.
- What we forecast
- Sales, traffic, inventory drawdown.
- Decisions that change
- How much to stock.
2026-08-18
DecompSSM: A Decomposition-Based State Space Model for Multivariate Time-Series Forecasting
Our forecasting model learns to decompose series into trend, seasonal and residual components end-to-end. Accepted at ICASSP 2026, it achieved the best accuracy in 28 of 32 standard benchmark settings.
2026-08-17
Demand Forecasting AI for Inventory Optimization
We supported an AI systems company in adopting state-of-the-art time-series forecasting, improving demand-forecast accuracy and reducing inventory losses in a merchandise management system.