AI summaryⓘ
The authors developed a machine learning model called a convolutional variational autoencoder to predict missing data in cryptocurrency options volatility surfaces for Bitcoin and Ethereum. They combined this model with a simpler method to create a hybrid predictor that is more accurate and reliable, especially when large parts of the data are missing. Their results show the hybrid greatly reduces prediction errors and works well even in difficult situations like missing entire sets of option strikes. Training the model on both cryptocurrencies together improved performance compared to training on each alone, suggesting similarities in their volatility patterns. The authors also released their code and data for others to verify and build upon their work.
convolutional variational autoencoderimplied volatility surfacecryptocurrency optionsBTCETHvolatility smiletenor-delta gridroot mean square errorarbitrage-freesurface completion
Authors
Sadanand Singh, Allam Reddy, Manan Chopra
Abstract
We present a convolutional variational autoencoder for cryptocurrency implied-volatility surfaces, together with a deployable predictor that combines it with a quadratic smile re-fit through a deterministic per-tenor routing rule. Trained on 6,034 fully-filled hourly Binance Options surfaces of BTC and ETH spanning May-October 2023 and parameterised on a common $6 \times 7$ tenor-delta grid, the model attains a hidden-cell surface-completion RMSE in the 0.94-1.56 vol-point range across both markets and mask rates 10-50%. The hybrid predictor attains 0.83 vol points at 50% masking against 7.00 for the smile re-fit alone, an eightfold reduction obtained at no additional inference cost. Under structurally-correlated hole patterns that emulate the withdrawal of an entire tenor of strikes, the smile re-fit incurs 9.6-13.1 vol points of error while the learned model remains at 1.5-1.9, isolating a regime in which the generative model is the only viable predictor. Joint training on BTC and ETH improves the in-distribution model on both markets by 9-27% relative to the better-performing single-symbol counterpart, indicating a substantially shared vol-surface manifold across the two largest cryptocurrencies over the observation window. The hybrid is calendar- and butterfly-arbitrage-free at the listed strikes, a property that the parametric smile re-fit alone fails at high mask rates. The per-snapshot reconstruction error of the trained model flags the late-October ETF-anticipation rally and the August $17$, $2023$ flash crash as elevated-error periods without supervision. All training and evaluation infrastructure is released to support reproducible follow-on work.