Understanding how price-volume information determines future price movement is important for market makers who frequently place orders on both buy and sell sides, and for traders to split meta-orders to reduce price impact. Given the complex non-linear nature of the problem, we consider the prediction of the movement direction of the mid-price on an option order book, using machine learning tools. The applicability of such tools on the options market is currently missing. On an intraday tick-level dataset of options on an exchange traded fund from the Chinese market, we apply a variety of machine learning methods, including decision tree, random forest, logistic regression, and long short-term memory neural network. As machine learning models become more complex, they can extract deeper hidden relationship from input features, which classic market microstructure models struggle to deal with. We discover that the price movement is predictable, deep neural networks with time-lagged features perform better than all other simpler models, and this ability is universal and shared across assets. Using an interpretable model-agnostic tool, we find that the first two levels of features are the most important for prediction. The findings of this article encourage researchers as well as practitioners to explore more sophisticated models and use more relevant features.
We study neural networks as nonparametric estimation tools for the hedging of options. To this end, we design a network, named HedgeNet, that directly outputs a hedging strategy. This network is trained to minimise the hedging error instead of the pricing error. Applied to end-of-day and tick prices of S&P 500 and Euro Stoxx 50 options, the network is able to reduce the mean squared hedging error of the Black-Scholes benchmark significantly. We illustrate, however, that a similar benefit arises by simple linear regressions that incorporate the leverage effect. Finally, we show how a faulty training/test data split, possibly along with an additional ‘tagging’ of data, leads to a significant overestimation of the outperformance of neural networks.
I. Understanding how information drives asset prices is a cornerstone of financial economics. Traditional asset pricing models, such as the Capital Asset Pricing Model (CAPM) and the Fama–French fa...
Understanding the risk-return trade-off in the options market is difficult with standard observable factor models. We examine whether dynamic factor loadings improve the explanation of the cross-section of delta-hedged option returns. We apply instrumented principal component analysis (IPCA) to major exchange-traded option products in China. IPCA allows conditional betas to vary with option characteristics, which addresses short contract lifespans and rapidly evolving characteristics. We find that a three-factor IPCA model explains 19.30% of variation in individual option returns and 99.23% in managed portfolios. A bootstrap asset-pricing test fails to reject a zero-alpha restriction. Observable factor models with characteristic-instrumented dynamic betas achieve performance close to IPCA, highlighting the importance of time-varying loadings. We also provide subsample and characteristic-importance analyses.
Financial time series forecasting is central to trading, portfolio optimization, and risk management, yet it remains challenging due to noisy, non-stationary, and heterogeneous data. Recent advances in time series foundation models (TSFMs), inspired by large language models, offer a new paradigm for learning generalizable temporal representations from large and diverse datasets. This paper presents the first comprehensive empirical study of TSFMs in global financial markets. Using a large-scale dataset of daily excess returns across diverse markets, we evaluate zero-shot inference, fine-tuning, and pre-training from scratch against strong benchmark models. We find that off-the-shelf pre-trained TSFMs perform poorly in zero-shot and fine-tuning settings, whereas models pre-trained from scratch on financial data achieve substantial forecasting and economic improvements, underscoring the value of domain-specific adaptation. Increasing the dataset size, incorporating synthetic data augmentation, and applying hyperparameter tuning further enhance performance.