Paper: arXiv 2406.11886
Authors: Haoren Zhu, Pengfei Zhao, Wilfred Siu Hung NG, Dik Lun Lee
Abstract
Financial assets exhibit complex dependency structures, which are crucial for investors to create diversified portfolios to mitigate risk in volatile financial markets. To explore the financial asset dependencies dynamics, we propose a novel approach that models the dependencies of assets as an Asset Dependency Matrix (ADM) and treats the ADM sequences as image sequences. This allows us to leverage deep learning-based video prediction methods to capture the spatiotemporal dependencies among assets. However, unlike images where neighboring pixels exhibit explicit spatiotemporal dependencies due to the natural continuity of object movements, assets in ADM do not have a natural order. This poses challenges to organizing the relational assets to reveal better the spatiotemporal dependencies among neighboring assets for ADM forecasting. To tackle the challenges, we propose the Asset Dependency Neural Network (ADNN), which employs the Convolutional Long Short-Term Memory (ConvLSTM) network, a highly successful method for video prediction. ADNN can employ static and dynamic transformation functions to optimize the representations of the ADM. Through extensive experiments, we demonstrate that our proposed framework consistently outperforms the baselines in the ADM prediction and downstream application tasks. This research contributes to understanding and predicting asset dependencies, offering valuable insights for financial market participants.
Complexity vs Empirical Score
- Math Complexity: 7.0/10
- Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
- Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 8.0)
Why this score: The paper introduces advanced deep learning concepts like ConvLSTM and MoE transformations, requiring knowledge of neural network architectures and spatiotemporal modeling, warranting high math complexity. It includes extensive experiments with baselines, application to portfolio risk reduction, and discusses implementation details, indicating strong empirical rigor.
Research Flowchart
flowchart TD A["Research Goal<br>Predict Financial Asset Dependencies"] --> B["Data<br>Time-series of asset returns"] B --> C["Methodology<br>Asset Dependency Matrix ADM"] C --> D["Core Innovation<br>Static/Dynamic Transformation<br>Optimizes Asset Ordering"] D --> E["Computational Model<br>ADNN with ConvLSTM<br>Video Prediction Approach"] E --> F["Outcomes<br>Superior ADM Prediction &<br>Downstream Portfolio Performance"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes the Asset Dependency Neural Network (ADNN) to predict future Asset Dependency Matrices using spatiotemporal deep learning.
Source sentence
To tackle the challenges, we propose the Asset Dependency Neural Network (ADNN), which employs the Convolutional Long Short-Term Memory (ConvLSTM) network
Assumes 3
- No short selling is allowed, i.e., asset weights are constrained to [0,1]. execution
Source sentence
For simplicity, we assume that no short selling is allowed, i.e. asset weight ωi ∈[0, 1].
- Prior knowledge of the future standard deviation vector is assumed to eliminate extra variability. model
Source sentence
we assume prior knowledge of the future standard deviation vector to eliminate the extra variability.
- The ADM has no natural ordering, requiring rearrangement for spatiotemporal modeling. data
Source sentence
assets in ADM do not have a natural order. This poses challenges to organizing the relational assets to reveal better the spatiotemporal dependencies among neighboring assets
Data
2005-09 – 2020-08 · S&P 100 / NASDAQ-100 / DJI-30 stocks · equities · monthly
- dataset 7 market-prices unknown
Source sentence
We randomly choose one stock dataset (dataset 7) as the source for constructing the diversified portfolio based on the predicted ADMs. All of the methods under evaluation build up their portfolios from the same 32 stocks in dataset 7
Costs
Not modeled
Finds 2
Sharpe 2.00 (benchmark 0.45) · annual return 12.1% · max drawdown 10.7%
- ADNN achieves lower portfolio risk (1.67×10⁻⁴) than DCC, improving risk by 13.9% over DCC and 24.8% over the Previous ADM baseline. performance
Source sentence
ADNN outperforms DCC with an average risk of 1.67 × 10−4, which ranks only second to the optimal portfolio. In terms of average risk, ADNN achieves an improvement of 24.8% over Previous and 13.9% over DCC.
- PT-ADNN, which uses both positional rearrangement and MoE transformation, yields the best prediction accuracy among ADNN variants. predictive-accuracy
Source sentence
After comparing multiple ADNN frameworks with different transformation functions, we can observe that PT-ADNN that utilizes both positional rearrangement and MoE transform…
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 41 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (109)
- Numerically stable generation of correlation matrices and their factors (2000)
- Monte Carlo methods in financial engineering (2004)
- Polynomial representation of pictures (1986)
- Fractal image coding: A review (1993)
- A review on image feature extraction and representation techniques (2013)
- PAGAN: Portfolio Analysis with Generative Adversarial Networks (2019) — link
- Convolutional LSTM network: A machine learning approach for precipitation nowcasting (2015) — link
- Deep multi-scale video prediction beyond mean square error (2015) — link
and 101 more
- Learning to decompose and disentangle representations for video prediction (2018) — link
- Stochastic variational video prediction (2017) — link
- Eidetic 3d lstm: A model for video prediction and beyond (2018)
- The Factor–Spline–GARCH model for high and low frequency correlations (2012)
- Machine Learning in Asset Management—Part 1: Portfolio Construction—Trading Strategies (2020)
- Machine Learning in Asset Management—Part 2: Portfolio Construction—Weight Optimization (2020)
- A Review on Deep Learning Techniques for Video Prediction (2020) — link
- Are betas best? (1978)
- Simple rules for optimal portfolio selection: the multi group case (1977)
- Out-of-sample tests of forecasting accuracy: an analysis and review (2000)
- Dependence structure and risk measure (2003)
- Estimating the dependence structure of share prices–implications for portfolio selection (1973)
- Sector rotation and monetary conditions (2008)
- On the assessment of risk: Some further considerations (1974)
- Accurate, large minibatch sgd: Training imagenet in 1 hour (2017) — link
- Betas and their regression tendencies (1975)
- A note on using cross-sectional information in Bayesian estimation of security betas (1973)
- 60 Years of portfolio optimization: Practical challenges and current trends (2014)
- Model-based deep reinforcement learning for dynamic portfolio optimization (2019) — link
- Continuous-time mean–variance portfolio selection: A reinforcement learning framework (2020)
- Dissemination of health information through social networks: Twitter and antibiotics (2010)
- Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation (1982)
- Generalized autoregressive conditional heteroskedasticity (1986) — link
- Deep learning for finance: deep portfolios (2017)
- A deep reinforcement learning framework for the financial portfolio management problem (2017) — link
- Adam: A method for stochastic optimization (2014) — link
- Building diversified portfolios that outperform out of sample (2016)
- Discovering Bayesian market views for intelligent asset allocation (2018)
- The Hitchhiker’s Guide to the Galaxy (1995) — link
- Portfolio Selection (1952)
- Anticipating Correlations: A New Paradigm for Risk Management (2011)
- Dynamic conditional correlation: A simple class of multivariate generalized autoregressive conditional heteroskedasticity models (2002)
- Large dynamic covariance matrices (2019)
- Building diversified portfolios that outperform out of sample (2016) — link
- Dynamics of market correlations: Taxonomy and portfolio analysis (2003) — link
- Clustering and information in correlation based financial networks (2004) — link
- Spread of risk across financial markets: Better to invest in the peripheries (2013) — link
- Interconnectedness risk and active portfolio management: The information-theoretic perspective (2019) — link
- Asset allocation: new evidence through network approaches (2019) — link
- Can machine learning-based portfolios outperform traditional risk-based portfolios? The need to account for covariance misspecification (2019) — link
- Ten things you should know about the dynamic conditional correlation representation (2013)
- Analysis of financial time series (2005)
- On estimating the expected return on the market: An exploratory investigation (1980) — link
- The Markowitz Optimization Enigma: Is ‘Optimized’ Optimal? (1989) — link
- The effect of errors in means, variances, and covariances on optimal portfolio choice (1993) — link
- Leverage aversion and risk parity (2012) — link
- Toward maximum diversification (2008) — link
- Modelling time-varying correlations of financial markets (2003)
- Sequence to Sequence Learning with Neural Networks (2014) — link
- Long Short-Term Memory (1997)
- Generating Sequences With Recurrent Neural Networks (2014) — link
- On the difficulty of training Recurrent Neural Networks (2013) — link
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer (2017) — link
- Modeling task relationships in multi-task learning with multi-gate mixture-of-experts (2018)
- Deep Learning (2016)
- Hierarchical mixtures of experts and the EM algorithm (1993) — link
- Unsupervised Learning of Video Representations using LSTMs (2016) — link
- A Review on Deep Learning Techniques for Video Prediction (2020) — link
- Representation Learning: A Review and New Perspectives (2013) — link
- Beyond Short Snippets: Deep Networks for Video Classification (2015) — link
- Learning Spatiotemporal Features with 3D Convolutional Networks (2015) — link
- Predrnn: Recurrent neural networks for predictive learning using spatiotemporal lstms (2017)
- Options on the maximum or the minimum of several assets (1987)
- Bivariate option pricing using dynamic copula models (2005) — link
- A capital asset pricing model with time-varying covariances (1988)
- Multivariate simultaneous generalized ARCH (1995)
- Multivariate GARCH models: a survey (2006)
- Asset pricing with a factor-ARCH covariance structure: Empirical estimates for treasury bills (1990)
- A multi-dynamic-factor model for stock returns (1992)
- Long short-term memory recurrent neural network architectures for large scale acoustic modeling (2014)
- Exploiting Spatio-Temporal Correlations with Multiple 3D Convolutional Neural Networks for Citywide Vehicle Flow Prediction (2018) — link
- End-to-end Prediction of Driver Intention using 3D Convolutional Neural Networks (2019) — link
- On the best quadratic approximation of nonlinear systems (2001) — link
- QAS: Real-Time Quadratic Approximation of Subdivision Surfaces (2007) — link
- Representation Learning: A Review and New Perspectives (2014) — link
- Image super-resolution via deep recursive residual network (2017)
- Learning factored representations in a deep mixture of experts (2013) — link
- Adaptive mixtures of local experts (1991)
- Forecasting Asset Dependencies to Reduce Portfolio Risk (2022)
- Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results (1998) — link
- Comparing unconstrained parametrization methods for return covariance matrix prediction (2022)
- Adaptive estimation of covariance matrices via cholesky decomposition (2010)
- Estimating risk parameters (1999)
- Regime changes and financial markets (2012)
- A global averaging method for dynamic time warping, with applications to clustering (2011)
- Business groups as hierarchies of firms: determinants of vertical integration and performance (2013)
- S_I_LSTM: stock price prediction based on multiple data sources and sentiment analysis (2022)
- A graph-based CNN-LSTM stock price prediction algorithm with leading indicators (2023)
- Financial time series forecasting with multi-modality graph neural network (2022)
- Multi-graph convolutional network for relationship-driven stock movement prediction (2021)
- A novel graph convolutional feature based convolutional neural network for stock trend prediction (2021)
- St-trader: A spatial-temporal deep neural network for modeling stock market movement (2021)
- Mean–variance portfolio optimization using machine learning-based stock price prediction (2021)
- Portfolio optimization with return prediction using deep learning and machine learning (2021)
- End-to-end risk budgeting portfolio optimization with neural networks (2023)
- Deep portfolio optimization via distributional prediction of residual factors (2021)
- Recent advances in reinforcement learning in finance (2023)
- Reinforcement-learning based portfolio management with augmented asset movement prediction states (2020)
- DeepTrader: a deep reinforcement learning approach for risk-return balanced portfolio management with market conditions Embedding (2021)
- Learning constitutive relations using symmetric positive definite neural networks (2021) — link
- Deep hashing-based dynamic stock correlation estimation via normalizing flow (2023)
0 of 109 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.