mlsanityData to 14 Oct 2026

Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis

arXiv 1712.00975 ↗First posted 4 Dec 2017cs.CE cs.LG q-fin.CPcited by 46

Not on the map. Why?

Abstract (arXiv)

Financial time-series forecasting has long been a challenging problem because of the inherently noisy and stochastic nature of the market. In the High-Frequency Trading (HFT), forecasting for trading purposes is even a more challenging task since an automated inference system is required to be both accurate and fast. In this paper, we propose a neural network layer architecture that incorporates the idea of bilinear projection as well as an attention mechanism that enables the layer to detect and focus on crucial temporal information. The resulting network is highly interpretable, given its ability to highlight the importance and contribution of each temporal instance, thus allowing further analysis on the time instances of interest. Our experiments in a large-scale Limit Order Book (LOB) dataset show that a two-hidden-layer network utilizing our proposed layer outperforms by a large margin all existing state-of-the-art results coming from much deeper architectures while requiring far fewer computations.

Key facts. Cited by 46 papers in the map (data through 14 Oct 2026). First posted on arXiv 4 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 12; 2023: 9; 2024: 4; 2025: 6; 2026: 3.

46 papers.

Sort:

By area:

  1. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  2. 2021Self-supervised Autoregressive Domain Adaptation for Time Series Datacited by 29
  3. 2022Bayesian Learning for Neural Networks: an algorithmic surveycited by 23
  4. 2024A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecastingcited by 14
  5. 2025Multi-period Learning for Financial Time Series Forecastingcited by 11
  6. 2021Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Unitscited by 10
  7. 2023LOB-Based Deep Learning Models for Stock Price Trend Prediction: A Benchmark Studycited by 9
  8. 2022Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series predictioncited by 8
  9. 2022Long Short-Term Memory Neural Network for Financial Time Seriescited by 8
  10. 2024HLOB -- Information Persistence and Structure in Limit Order Bookscited by 8
  11. 2022Distributional Drift Adaptation with Temporal Conditional Variational Autoencoder for Multivariate Time Series Forecastingcited by 7
  12. 2024Deep Limit Order Book Forecastingcited by 7
34 more
  1. 2021Tensor-Train Recurrent Neural Networks for Interpretable Multi-Way Financial Forecastingcited by 6
  2. 2021How Robust are Limit Order Book Representations under Data Perturbation?cited by 6
  3. 2021AURSAD: Universal Robot Screwdriving Anomaly Detection Datasetcited by 5
  4. 2022Fighting Money Laundering with Statistics and Machine Learningcited by 5
  5. 2022Bayesian Bilinear Neural Network for Predicting the Mid-price Dynamics in Limit-Order Book Marketscited by 5
  6. 2022Augmented Bilinear Network for Incremental Multi-Stock Time-Series Classificationcited by 4
  7. 2022Axial-LOB: High-Frequency Trading with Axial Attentioncited by 4
  8. 2025TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Datacited by 4
  9. 2022Quasi Black-Box Variational Inference with Natural Gradients for Bayesian Learningcited by 3
  10. 2025Explaining the Unexplainable: A Systematic Review of Explainable AI in Financecited by 3
  11. 2021Detecting Faults during Automatic Screwdriving: A Dataset and Use Case of Anomaly Detection for Automatic Screwdrivingcited by 2
  12. 2021Low-Rank Temporal Attention-Augmented Bilinear Network for financial time-series forecastingcited by 2
  13. 2021Bilinear Input Normalization for Neural Networks in Financial Forecastingcited by 2
  14. 2023Optimum Output Long Short-Term Memory Cell for High-Frequency Trading Forecastingcited by 2
  15. 2023Copula Variational LSTM for High-dimensional Cross-market Multivariate Dependence Modelingcited by 2
  16. 2024Time-Series Foundation AI Model for Value-at-Risk Forecastingcited by 2
  17. 2025LOBERT: Generative AI Foundation Model for Limit Order Book Messagescited by 2
  18. 2022Manifold Gaussian Variational Bayes on the Precision Matrixcited by 1
  19. 2022Predicting the State of Synchronization of Financial Time Series using Cross Recurrence Plotscited by 1
  20. 2023Local-Global Methods for Generalised Solar Irradiance Forecastingcited by 1
  21. 2023Market Making with Deep Reinforcement Learning from Limit Order Bookscited by 1
  22. 2023Leveraging Deep Learning and Online Source Sentiment for Financial Portfolio Managementcited by 1
  23. 2023Combining Deep Learning on Order Books with Reinforcement Learning for Profitable Tradingcited by 1
  24. 2021Visualising Deep Network's Time-Series Representationscited by 0
  25. 2021Knowledge Distillation By Sparse Representation Matchingcited by 0
  26. 2021Memory Capacity of Recurrent Neural Networks with Matrix Representationcited by 0
  27. 2021DeepTimeAnomalyViz: A Tool for Visualizing and Post-processing Deep Learning Anomaly Detection Results for Industrial Time-Seriescited by 0
  28. 2023Performance Evaluation of Equal-Weight Portfolio and Optimum Risk Portfolio on Indian Stockscited by 0
  29. 2023Cryptocurrency Portfolio Optimization by Neural Networkscited by 0
  30. 2025FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMscited by 0
  31. 2025TABL-ABM: A Hybrid Framework for Synthetic LOB Generationcited by 0
  32. 2026The Inference-Compute Frontier and a Latency-Efficient Architecture for Limit Order Book Predictioncited by 0
  33. 2026Repurposing Deep Limit Order Book Forecasting for Scenario-Conditioned Market Impact Modelingcited by 0
  34. 2026UQ-LOB: Uncertainty-Aware Limit Order Book Mid-Price Forecastingcited by 0