Portfolio Construction

Diffusion Variational Autoencoder for Tackling Stochasticity in Multi-Step Regression Stock Price Prediction ArXiv ID: 2309.00073 “View on arXiv” Authors: Unknown Abstract Multi-step stock price prediction over a long-term horizon is crucial for forecasting its volatility, allowing financial institutions to price and hedge derivatives, and banks to quantify the risk in their trading books. Additionally, most financial regulators also require a liquidity horizon of several days for institutional investors to exit their risky assets, in order to not materially affect market prices. However, the task of multi-step stock price prediction is challenging, given the highly stochastic nature of stock data. Current solutions to tackle this problem are mostly designed for single-step, classification-based predictions, and are limited to low representation expressiveness. The problem also gets progressively harder with the introduction of the target price sequence, which also contains stochastic noise and reduces generalizability at test-time. To tackle these issues, we combine a deep hierarchical variational-autoencoder (VAE) and diffusion probabilistic techniques to do seq2seq stock prediction through a stochastic generative process. The hierarchical VAE allows us to learn the complex and low-level latent variables for stock prediction, while the diffusion probabilistic model trains the predictor to handle stock price stochasticity by progressively adding random noise to the stock data. Our Diffusion-VAE (D-Va) model is shown to outperform state-of-the-art solutions in terms of its prediction accuracy and variance. More importantly, the multi-step outputs can also allow us to form a stock portfolio over the prediction length. We demonstrate the effectiveness of our model outputs in the portfolio investment task through the Sharpe ratio metric and highlight the importance of dealing with different types of prediction uncertainties. ...

ChatGPT Informed Graph Neural Network for Stock Movement Prediction ArXiv ID: 2306.03763 “View on arXiv” Authors: Unknown Abstract ChatGPT has demonstrated remarkable capabilities across various natural language processing (NLP) tasks. However, its potential for inferring dynamic network structures from temporal textual data, specifically financial news, remains an unexplored frontier. In this research, we introduce a novel framework that leverages ChatGPT’s graph inference capabilities to enhance Graph Neural Networks (GNN). Our framework adeptly extracts evolving network structures from textual data, and incorporates these networks into graph neural networks for subsequent predictive tasks. The experimental results from stock movement forecasting indicate our model has consistently outperformed the state-of-the-art Deep Learning-based benchmarks. Furthermore, the portfolios constructed based on our model’s outputs demonstrate higher annualized cumulative returns, alongside reduced volatility and maximum drawdown. This superior performance highlights the potential of ChatGPT for text-based network inferences and underscores its promising implications for the financial sector. ...

E2EAI: End-to-End Deep Learning Framework for Active Investing ArXiv ID: 2305.16364 “View on arXiv” Authors: Unknown Abstract Active investing aims to construct a portfolio of assets that are believed to be relatively profitable in the markets, with one popular method being to construct a portfolio via factor-based strategies. In recent years, there have been increasing efforts to apply deep learning to pursue “deep factors’’ with more active returns or promising pipelines for asset trends prediction. However, the question of how to construct an active investment portfolio via an end-to-end deep learning framework (E2E) is still open and rarely addressed in existing works. In this paper, we are the first to propose an E2E that covers almost the entire process of factor investing through factor selection, factor combination, stock selection, and portfolio construction. Extensive experiments on real stock market data demonstrate the effectiveness of our end-to-end deep leaning framework in active investing. ...

A Study of Saving and Investment Behaviour of Individual Households – An Empirical Evidence from Orissa ArXiv ID: ssrn-2168305 “View on arXiv” Authors: Unknown Abstract Investment is one of the foremost concerns of every individual investor as their small savings of today are to meet the expenses of tomorrow. Taking 200 respond Keywords: Retail Investing, Portfolio Construction, Savings Behavior, Asset Allocation, Multi-Asset Complexity vs Empirical Score Math Complexity: 2.0/10 Empirical Rigor: 5.5/10 Quadrant: Street Traders Why: The paper applies standard statistical tests (Chi-Square, ANOVA, Rank Correlation) with basic formulas but no advanced derivations, placing math complexity low. Its empirical rigor is moderate because it uses a structured questionnaire and primary data collection for backtest-like analysis of investor behavior, though it lacks high-frequency data or algorithmic implementation. flowchart TD A["Research Goal: Analyze saving & investment behavior<br>of households in Orissa"] --> B["Methodology: Empirical Analysis<br>Survey Data Collection"] B --> C["Data Inputs: 200 Households<br>Demographics, Income, Assets"] C --> D["Computational Process: Multi-Asset<br>Portfolio Analysis & Allocation"] D --> E["Key Outcomes: Specific patterns in<br>Savings Behavior & Retail Investing"]

Low Risk Stocks Outperform within All Observable Markets of the World ArXiv ID: ssrn-2055431 “View on arXiv” Authors: Unknown Abstract This article provides global evidence supporting the Low Volatility Anomaly: that low risk stocks consistently provide higher returns than high risk stocks. T Keywords: Low Volatility Anomaly, Risk-Adjusted Returns, High Risk Stocks, Portfolio Construction, Equities Complexity vs Empirical Score Math Complexity: 3.0/10 Empirical Rigor: 8.0/10 Quadrant: Street Traders Why: The paper presents a clear, implementable backtesting procedure with global data across 33 markets, showing statistical results like return differences and Sharpe ratios, but relies primarily on descriptive statistics and basic volatility rankings rather than advanced mathematical derivations. flowchart TD A["Research Goal:<br>Test Low Volatility Anomaly<br>across global equity markets"] --> B["Data Inputs:<br>Global stock data from<br>33 countries (1990-2019)"] B --> C["Methodology:<br>Sort stocks into volatility<br>quintiles by market/country"] C --> D["Computational Process:<br>Calculate returns, Sharpe ratios,<br>and CAPM alphas for each quintile"] D --> E{"Outcomes / Findings"} E --> F["Low volatility stocks<br>outperform high volatility stocks"] E --> G["Risk-adjusted returns (Sharpe)<br>are superior for low risk portfolios"] E --> H["Anomaly persists across<br>all observable markets"]

Diversified Statistical Arbitrage: Dynamically Combining Mean Reversion and Momentum Strategies ArXiv ID: ssrn-1666799 “View on arXiv” Authors: Unknown Abstract This paper presents a quantitative investment strategy that is capable of producing strong risk-adjusted returns in both up and down markets. The strategy combi Keywords: Quantitative investment strategy, Risk-adjusted returns, Momentum, Reversal, Portfolio construction Complexity vs Empirical Score Math Complexity: 7.5/10 Empirical Rigor: 6.0/10 Quadrant: Holy Grail Why: The paper employs advanced mathematical techniques like Principal Component Analysis (PCA) with eigenvalues and eigenvectors for decomposition, indicating high mathematical density. It also presents in-sample and out-of-sample performance analysis across multiple market environments (2008-2009), suggesting significant empirical testing and implementation focus. flowchart TD A["Research Goal: Develop a Quantitative Investment Strategy"] --> B["Methodology: Diversified Statistical Arbitrage"] B --> C["Data: Historical Stock Prices & Market Data"] C --> D{"Compute Signal Generation"} D --> E["Mean Reversion Strategy"] D --> F["Momentum Strategy"] E & F --> G["Dynamic Portfolio Construction"] G --> H["Key Findings: Strong Risk-Adjusted Returns"] H --> I["Outcomes: Effective in Both Up & Down Markets"]