DiffSTOCK: Probabilistic relational Stock Market Predictions using Diffusion Models (2403.14063v1)
Abstract: In this work, we propose an approach to generalize denoising diffusion probabilistic models for stock market predictions and portfolio management. Present works have demonstrated the efficacy of modeling interstock relations for market time-series forecasting and utilized Graph-based learning models for value prediction and portfolio management. Though convincing, these deterministic approaches still fall short of handling uncertainties i.e., due to the low signal-to-noise ratio of the financial data, it is quite challenging to learn effective deterministic models. Since the probabilistic methods have shown to effectively emulate higher uncertainties for time-series predictions. To this end, we showcase effective utilisation of Denoising Diffusion Probabilistic Models (DDPM), to develop an architecture for providing better market predictions conditioned on the historical financial indicators and inter-stock relations. Additionally, we also provide a novel deterministic architecture MaTCHS which uses Masked Relational Transformer(MRT) to exploit inter-stock relations along with historical stock features. We demonstrate that our model achieves SOTA performance for movement predication and Portfolio management.
- “Deep learning for stock prediction using numerical and text info.,” 15th ICIS, 2016.
- K Chen and Zhou, “A LSTM-based method for stock returns,” 2015 IEEE Big Data.
- “Deep learning for event-driven stock prediction,” 24th IJCAI, 2015.
- “Dl for stock market pred. from financial news,” 2017 IEEE CIVEMSA.
- R Sawhney and RR Shah, “Stock selection via sthan: A learning to rank approach,” in AAAI, 2021.
- F Feng and Tat-Seng C, “Temp. relational ranking for stock pred.,” ACM Trans. on Info. Systems (TOIS), 2019.
- R Hyndman and Ralph D, Forecasting with expo smoothing, Springer Science & Business Media, 2008.
- Time series analysis, John Wiley & Sons, 2015.
- K Bandara and S Smyl, “Forecasting across time series databases,” Expert systems with applications, 2020.
- S Makridakis and V Assimakopoulos, “Stat. and ml forecasting methods,” PloS one, 2018.
- K Rasul and R Vollgraf, “Autoregressive ddpm for multi. prob. time series forecasting,” in ICML. PMLR, 2021.
- Y Tashiro and S Ermon, “Csdi for probabilistic time series imputation,” NIPS, 2021.
- R Israel and T J M, “Can machines’ learn’finance?,” Journal of Investment Management, 2020.
- “Diffuion models,” NIPS, 2020.
- D. Daiya and Che Lin, “Stock movement prediction and portfolio management via multimodal learning with transformer,” in ICASSP 2021. IEEE, 2021.
- “Stock movement prediction that integrates het. data sources using dilated causal conv.,” in (ICASSP), 2020.
- “Diffstg: Probabilistic spatio-temporal graph forecasting with denoising diffusion models,” arXiv preprint arXiv:2301.13629, 2023.
- I Assent and T Seidl, “Dtw for efficient similarity search in timeseries databases,” VLDB Endowment, 2009.
- “Attention is all you need,” Advances in neural information processing systems, vol. 30, 2017.
- P Michel and G Neubig, “Are 16 heads really better than one?,” NIPS, 2019.
- E Voita and I Titov, “Analyzing multi-head self-attention,” arXiv preprint arXiv:1905.09418, 2019.
- J Lu and S Lee, “12-in-1,” in CVPR, 2020.
- Yumo Xu and SB Cohen, “Stock movement prediction from tweets and historical prices,” in ACL, 2018.
- Ramit S and RR Shah, “Spatiotemporal hcn for stock movement forecasting,” in ICDM, 2020.
- “Inc. corp. relationship via gcnn for stock price prediction,” in CIKM, 2018.
- “HATS: A hier. graph attention network for stock movement pred.,” in arXiv, 2019.
- Robert Goodell Brown, Smoothing, forecasting and prediction of discrete time series, Courier Corporation, 2004.
- S Selvin and KP Soman, “Stock price prediction using lstm, rnn and cnn-sliding window model,” in 2017 (icacci). IEEE, 2017.
- V Pagolu and B Majhi, “Sentiment analysis for predicting stock market movements,” in 2016 (SCOPES). IEEE.
- K Nguyen, THand Shirai, “Topic modeling based stock market pred.,” in ACL, 2015.
- Z Hu and TY Liu, “Listening to chaotic whispers,” WSDM ’18.
- R Sawhney and RR Shah, “Deep attentive learning for stock mov. pred.,” in (EMNLP), 2020.
- F Feng and TS Chua, “Enhancing stock mov. pred. with adversarial training,” arXiv preprint arXiv:1810.09936, 2018.
- S Carta and A Sanna, “Multi-dqn: An ensemble of deep q-learning agents for stock market forecasting,” Expert systems with applications, 2021.
- Y Liu and C Liu, “Adaptive quant. trading: An imitative deep reinforcement learning approach,” in AAAI, 2020.
- W Bao and Y Rao, “A dl framework for financial time series using lstm,” PloS one, 2017.