Martin Magris, Mostafa Shabani, Alexandros Iosifidis
arXiv 7 Mar 2022 · Econometrics · publishedJournal of Forecasting (2023) · 17 citations (OpenAlex)
arXiv:2203.03613 · PDF · DOI · OpenAlex · Extracted main text
The prediction of financial markets is a challenging yet important task. In modern electronically-driven markets, traditional time-series econometric methods often appear incapable of capturing the true complexity of the multi-level interactions driving the price dynamics. While recent research has established the effectiveness of traditional machine learning (ML) models in financial applications, their intrinsic inability to deal with uncertainties, which is a great concern in econometrics research and real business applications, constitutes a major drawback. Bayesian methods naturally appear as a suitable remedy conveying the predictive ability of ML methods with the probabilistically-oriented practice of econometric research. By adopting a state-of-the-art second-order optimization algorithm, we train a Bayesian bilinear neural network with temporal attention, suitable for the challenging time-series task of predicting mid-price movements in ultra-high-frequency limit-order book markets. We thoroughly compare our Bayesian model with traditional ML alternatives by addressing the use of predictive distributions to analyze errors and uncertainties associated with the estimated parameters and model forecasts. Our results underline the feasibility of the Bayesian deep-learning approach and its predictive and decisional advantages in complex econometric tasks, prompting future research in this direction.
appendix boundary found by appendix_command · 91% of the source is main text. Read the extracted text to check this.
The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.
| Reference | Intensity | Mentions | Sections | Main text | |
|---|---|---|---|---|---|
| 1 | K. Osawa, S. Swaroop, M. E. Khan, A. Jain, R. Eschenhagen, R. E. Tur… (2019) Practical deep learning with bayesian principles | 0.928 | 4 | 3 | 100% |
| 2 | D. T. Tran, A. Iosifidis, J. Kanniainen, and M. Gabbouj, “Temporal A… (2019) Temporal Attention-Augmented Bilinear Network for Financial Time-Series Data Analysis | 0.928 | 4 | 3 | 100% |
| 3 | Y. Gal and Z. Ghahramani, “Dropout as a bayesian approximation: Repr… (2016) Dropout as a bayesian approximation: Representing model uncertainty in deep learning | 0.811 | 4 | 2 | 100% |
| 4 | A. Ntakaris, M. Magris, J. Kanniainen, M. Gabbouj, and A. Iosifidis,… (2018) Benchmark dataset for mid-price forecasting of limit order book data with machine learning methods | 0.737 | 3 | 2 | 100% |
| 5 | C. Blundell, J. Cornebise, K. Kavikcuoglu, and D. Wierstra, “Weight… (2015) Weight uncertainty in neural networks | 0.644 | 2 | 2 | 100% |
| 6 | M. Shabani, D. T. Tran, M. Magris, J. Kanniainen, and A. Iosifidis,… (2022) Multi-head temporal attention-augmented bilinear network for financial time series prediction | 0.644 | 2 | 2 | 100% |
| 7 | A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj, an… (2017) Forecasting stock prices from the limit order book using convolutional neural networks | 0.644 | 2 | 2 | 100% |
| 8 | A. Tsantekidis, N. Passalis, A. Tefas, J. Kanniainen, M. Gabbouj, an… (2020) Using deep learning for price prediction by exploiting stationary limit order book features | 0.644 | 2 | 2 | 100% |
| 9 | E. Goan and C. Fookes, Bayesian Neural Networks: An Introduction and… (2020) ch. 3, pp | 0.511 | 2 | 1 | 100% |
| 10 | M. E. Khan and W. Lin, “Conjugate-computation variational inference:… (2017) Conjugate-computation variational inference: converting variational inference in non-conjugate models to inferences in conjugate… | 0.511 | 2 | 1 | 100% |
Showing the top 10 of 69 scored citations.