Static Badge License: MIT Status Org Platform
AutoPred is a lightweight predictive modelling web application for small and medium-sized businesses.
It turns historical data into forecasts, compares models, and produces decision-ready outputs through simple and explainable workflows.
AutoPred focuses on:
- practical forecasting, not complex modelling
- clear model comparison and selection
- business-friendly visualisations
- structured outputs ready for dashboards
Find more on AutoPred website and bakery demo
- Features
- Key Capabilities
- Example Demo
- Analysis
- Position in Sloxen Stack
- What Makes It different
- Roadmap
- Contribution
- License
- Links
AutoPred helps answer practical business questions:
- How much will we sell tomorrow?
- Which products are predictable?
- When does demand change?
- How much better is our model than a simple baseline?
It focuses on clarity, not complexity.
- Structured train, validation, and test workflow
- Baseline comparison using dummy models
- Multiple model training and selection
- Exportable prediction datasets
- Business-friendly visualisations
- Ready for web-based dashboards
A full working example is available
The bakery demo shows:
- demand prediction across multiple products
- model comparison and selection
- evaluation on unseen data
- visual outputs designed for business users
This demo represents a real use case of AutoPred in action.
AutoPred generates structured outputs:
- scored datasets
- model comparison tables
- final metrics
- visualisation-ready data
These outputs can be directly used in dashboards or applications. AutoPred visualisations are designed to be:
- simple to read
- focused on key insights
- suitable for non-technical users
They highlight:
- actual vs predicted trends
- model improvement over baseline
- product-level prediction accuracy
AutoPred sits alongside other Sloxen tools:
- AutoTrac → data tracking and logging
- AutoPred → data integration and preparation
- AutoPred → prediction and forecasting
- AutoVisuals → automated content generation
Together, they form a simple pipeline from raw data to decision-ready insights.
AutoPred is designed for usability:
- no black-box modelling focus
- baseline-first comparison (dummy model)
- transparent model selection
- outputs that can be directly used in business dashboards
The goal is not to build the most complex model, but the most useful one.
AutoPred is evolving into a web-based service.
Planned features:
- interactive dashboards
- drag-and-drop data upload
- model selection in browser
- real-time forecasting
- API access
The bakery demo is an early instance of this system.
Maintained by SloxenTM GitHub, and Daddy Sloth.
© 2026 SloxenTM.
A trading name of Sloxen Ltd Registered in England and Wales (Company No. 16907507).
MIT License.