Deep Learning for Financial Time Series: A Large-Scale Benchmark of Risk-Adjusted Performance

• URL: http://arxiv.org/abs/2603.01820v1
• Date: Mon, 02 Mar 2026 12:52:50 GMT
• Title: Deep Learning for Financial Time Series: A Large-Scale Benchmark of Risk-Adjusted Performance
• Authors: Adir Saly-Kaufmann, Kieran Wood, Jan Peter-Calliess, Stefan Zohren,
• Abstract summary: We present a large scale benchmark of modern deep learning architectures for a financial time series prediction and position sizing task.<n>We evaluate linear models, recurrent networks, transformer based architectures, state space models, and recent sequence representation approaches.<n>We find that models explicitly designed to learn rich temporal representations consistently outperform linear benchmarks and generic deep learning models.
• Score: 4.889402269887708
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a large scale benchmark of modern deep learning architectures for a financial time series prediction and position sizing task, with a primary focus on Sharpe ratio optimization. Evaluating linear models, recurrent networks, transformer based architectures, state space models, and recent sequence representation approaches, we assess out of sample performance on a daily futures dataset spanning commodities, equity indices, bonds, and FX spanning 2010 to 2025. Our evaluation goes beyond average returns and includes statistical significance, downside and tail risk measures, breakeven transaction cost analysis, robustness to random seed selection, and computational efficiency. We find that models explicitly designed to learn rich temporal representations consistently outperform linear benchmarks and generic deep learning models, which often lead the ranking in standard time series benchmarks. Hybrid models such as VSN with LSTM, a combination of Variable Selection Networks (VSN) and LSTMs, achieves the highest overall Sharpe ratio, while VSN with xLSTM and LSTM with PatchTST exhibit superior downside adjusted characteristics. xLSTM demonstrates the largest breakeven transaction cost buffer, indicating improved robustness to trading frictions.

Related papers

• Trend-Adjusted Time Series Models with an Application to Gold Price Forecasting [0.0]
  Time series data play a critical role in various fields, including finance, healthcare, marketing, and engineering.<n>We propose the Trend-Adjusted Time Series (TATS) model, which adjusts the forecasted values based on the predicted trend.
  arXiv  Detail & Related papers  (2026-01-19T04:09:53Z)
• StockBot 2.0: Vanilla LSTMs Outperform Transformer-based Forecasting for Stock Prices [0.0]
  We present an enhanced StockBot architecture that systematically evaluates modern attention-based, convolutional, and recurrent time-series forecasting models.<n>A carefully constructed vanilla LSTM consistently achieves superior predictive accuracy and more stable buy/sell decision-making.
  arXiv  Detail & Related papers  (2026-01-01T04:09:51Z)
• Estimating Time Series Foundation Model Transferability via In-Context Learning [74.65355820906355]
  Time series foundation models (TSFMs) offer strong zero-shot forecasting via large-scale pre-training.<n>Fine-tuning remains critical for boosting performance in domains with limited public data.<n>We introduce TimeTic, a transferability estimation framework that recasts model selection as an in-context-learning problem.
  arXiv  Detail & Related papers  (2025-09-28T07:07:13Z)
• BreakGPT: Leveraging Large Language Models for Predicting Asset Price Surges [55.2480439325792]
  This paper introduces BreakGPT, a novel large language model (LLM) architecture adapted specifically for time series forecasting and the prediction of sharp upward movements in asset prices. We showcase BreakGPT as a promising solution for financial forecasting with minimal training and as a strong competitor for capturing both local and global temporal dependencies.
  arXiv  Detail & Related papers  (2024-11-09T05:40:32Z)
• Bridging SFT and DPO for Diffusion Model Alignment with Self-Sampling Preference Optimization [67.8738082040299]
  Self-Sampling Preference Optimization (SSPO) is a new alignment method for post-training reinforcement learning.<n>SSPO eliminates the need for paired data and reward models while retaining the training stability of SFT.<n>SSPO surpasses all previous approaches on the text-to-image benchmarks and demonstrates outstanding performance on the text-to-video benchmarks.
  arXiv  Detail & Related papers  (2024-10-07T17:56:53Z)
• Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [64.67540769692074]
  Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date.<n>We introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models.<n>Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench.
  arXiv  Detail & Related papers  (2024-10-04T04:56:11Z)
• LTSM-Bundle: A Toolbox and Benchmark on Large Language Models for Time Series Forecasting [69.33802286580786]
  We introduce LTSM-Bundle, a comprehensive toolbox, and benchmark for training LTSMs.<n>It modularized and benchmarked LTSMs from multiple dimensions, encompassing prompting strategies, tokenization approaches, base model selection, data quantity, and dataset diversity.<n> Empirical results demonstrate that this combination achieves superior zero-shot and few-shot performances compared to state-of-the-art LTSMs and traditional TSF methods.
  arXiv  Detail & Related papers  (2024-06-20T07:09:19Z)
• Application of Deep Learning for Factor Timing in Asset Management [21.212548040046133]
  More flexible models have better performance in explaining the variance in factor premium of the unseen period. For flexible models like neural networks, the optimal weights based on their prediction tend to be unstable. We verify that tilting down the rebalance frequency according to the historical optimal rebalancing scheme can help reduce the transaction costs.
  arXiv  Detail & Related papers  (2024-04-27T21:57:17Z)
• Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting [46.63798583414426]
  Long-term time series forecasting (LTSF) represents a critical frontier in time series analysis. Our study demonstrates, through both analytical and empirical evidence, that decomposition is key to containing excessive model inflation. Remarkably, by tailoring decomposition to the intrinsic dynamics of time series data, our proposed model outperforms existing benchmarks.
  arXiv  Detail & Related papers  (2024-01-22T13:15:40Z)
• Long Short-Term Memory Neural Network for Financial Time Series [0.0]
  We present an ensemble of independent and parallel long short-term memory neural networks for the prediction of stock price movement. With a straightforward trading strategy, comparisons with a randomly chosen portfolio and a portfolio containing all the stocks in the index show that the portfolio resulting from the LSTM ensemble provides better average daily returns and higher cumulative returns over time.
  arXiv  Detail & Related papers  (2022-01-20T15:17:26Z)
• Prediction of financial time series using LSTM and data denoising methods [0.29923891863939933]
  This paper proposes an ensemble method based on data denoising methods, including the wavelet transform (WT) and singular spectrum analysis (SSA) As WT and SSA can extract useful information from the original sequence and avoid overfitting, the hybrid model can better grasp the sequence pattern of the closing price of the DJIA.
  arXiv  Detail & Related papers  (2021-03-05T07:32:36Z)
• Deep Stock Predictions [58.720142291102135]
  We consider the design of a trading strategy that performs portfolio optimization using Long Short Term Memory (LSTM) neural networks. We then customize the loss function used to train the LSTM to increase the profit earned. We find the LSTM model with the customized loss function to have an improved performance in the training bot over a regressive baseline such as ARIMA.
  arXiv  Detail & Related papers  (2020-06-08T23:37:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.