oliverguhr/transformer-time-series-prediction resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1453 stars · 259 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A proof-of-concept repository with two PyTorch transformer models for single-step and multi-step time series prediction. It is educational demo code, with the author directing serious use to the flow-forecast package.

Use cases

• learn how to build a transformer for time series forecasting
• predict future values from historical time series data
• example of single-step and multi-step prediction in PyTorch
• starting point for transformer-based forecasting experiments
• understand how transformers capture long-term trends in sequences

When to choose

• you want readable reference code for transformer time series models
• you are learning PyTorch and sequence prediction
• you need a minimal demo of multi-step forecasting

When to avoid

• you need production-ready, efficient, or bug-free forecasting
• you want a maintained library with full features - use flow-forecast instead
• you need guaranteed correctness for critical workloads

Facets

learning-resource · maturity maintenance

machine-learning deep-learning time-series deep-learning machine-learning python transformer pytorch time-series-forecasting proof-of-concept

Member repositories

For agents

markdown · JSON · MCP: product_card(name="oliverguhr/transformer-time-series-prediction")