Hestonlabs
Model Card

Latent

A convolutional autoencoder that compresses 28 financial instruments into a 128-dimensional latent vector, capturing regime-level cross-asset behaviour.

Model Type

Conv. AE

Output Dims

128

Input Assets

28

Input Window

720h

Architecture

Latent is a convolutional autoencoder designed around spatio-temporal methods for multi-variate financial time series. The architecture was developed through research into how convolutional operations can capture both the temporal dynamics within each asset and the cross-asset spatial relationships across the input at each timestep.

The encoder takes a rolling 720-hour window of the 28 input instruments and compresses it into a fixed 128-dimensional vector. The decoder reconstructs the input from this embedding, training the latent space to retain only the structure most critical for explaining cross-asset co-movement and regime transitions.

The resulting embedding is a compact, continuous representation of the current market state — analogous to a coordinate in a learned regime space.

Training Data

Hourly price data across all 28 instruments, spanning 2008 to 2017. The training window covers the 2008 GFC and recovery, the European sovereign debt crisis, and multiple FX and commodity regime shifts — providing the model with a broad sample of cross-asset stress and correlation behaviour.

Equities & Volatility

  • FTSE100
  • SP500
  • NIKKEI
  • VIX

FX

  • DXY
  • EUR-USD
  • GBP-USD
  • USD-JPY
  • USD-CHF
  • USD-CAD
  • AUD-USD
  • NZD-USD
  • EUR-JPY
  • EUR-GBP
  • EUR-AUD
  • EUR-CHF
  • GBP-JPY
  • GBP-AUD
  • AUD-JPY
  • NZD-JPY

Rates

  • US2Y
  • US10Y
  • UK2Y
  • UK10Y
  • Germany2Y
  • Germany10Y

Precious Metals

  • XAU-USD
  • XAG-USD

Intended Use

  • Regime detection and classification across market cycles
  • Cross-asset correlation analysis and contagion mapping
  • Risk signal generation ahead of structural market shifts
  • Feature input for downstream financial ML models
  • Research into latent structure of multi-asset markets

Limitations

  • Trained on historical data — may not generalise to unprecedented market structures
  • Embedding dimensions have no guaranteed semantic interpretation
  • Does not directly predict prices, returns, or volatility
  • Coverage limited to the 28 included instruments; idiosyncratic signals from other assets are not captured
  • Regime labels are inferred post-hoc; the model is unsupervised and does not output named regimes