buffers.ai
6.1#6 in inventory optimization softwareFrom $25 a monthWeb
Visit| Fact | buffers.ai | supplychainpy |
|---|---|---|
| Forecasting | Forecasting backtests TimesFM, LightGBM, Prophet, Exponential Smoothing, and Moving Average over a rolling six-month window and selects a champion model per SKU. | The features page lists simple exponential smoothing and Holt’s trend corrected exponential smoothing; ARIMA models are marked as under development. |
| Founded | 2015 | 2016 |
| Input data | The minimum input is one row per SKU per day with date, SKU identifier, and units sold; CSV or XLSX uploads can be used for a benchmark without ERP work. | The project describes using CSV or text files and data from a database through a data API or ORM such as SQLAlchemy. |
| Integrations | Production integrations use recurring batch feeds configured for the customer’s stack; FTP-based ERP exchange has been used, and the maker publishes no list of named pre-built ERP or POS connectors. | The maker describes use with Pandas, Jupyter, Matplotlib, openpyxl and xlwings. |
| Target users | Replenishment is designed for replenishment, allocation, and merchandising teams shipping from a central warehouse to store chains, as well as store managers. | The project describes itself as a decision-support tool for analysts in commercial inventory and demand-planning roles. |
buffers.ai is aimed at retail and manufacturing enterprises, including replenishment, allocation, and merchandising teams serving store chains from a central warehouse, as well as store managers.
supplychainpy suits analysts working in commercial inventory and demand planning who want a Python-based decision-support tool. It is also relevant to users working with Pandas DataFrames, CSV or text files, or database-supplied data.