---
title: Quant Letter No. 36: February 2024, Week 1
url: https://www.ml-quant.com/issues/2024-02-07/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
issue_date: 2024-02-07
---


# Quant Letter No. 36: February 2024, Week 1

Sent 2024-02-07. 98 items.

## arXiv

### Finance

- __[Adaptive Portfolio Management with Multi-Agent Framework](https://arxiv.org/abs/2402.00515)__: The piece introduces a multi-agent and self-adaptive framework (MASA) for portfolio management, using reinforcement learning to balance returns and risks, providing market trend feedback and outperforming other similar approaches. (2024-02-01, shares: 4) · https://www.ml-quant.com/papers/arxiv/2402.00515/
- __[Extending Pearson's Correlation for Multi-Asset Portfolios](https://arxiv.org/abs/2402.00543)__: The article discusses the application of random matrix theory to extend Pearson's correlation coefficient to multiple variables, enhancing risk assessment in multi-asset portfolios and aiding in feature selection in classification. (2024-02-01, shares: 4) · https://www.ml-quant.com/papers/arxiv/2402.00543/
- __[Enhanced Volatility Forecasting for Oil Commodities](https://arxiv.org/abs/2402.01354)__: The article proposes a new method for forecasting oil-based volatility that models varying persistence shocks together, improving predictions and surpassing standard models. (2024-02-02, shares: 7) · https://www.ml-quant.com/papers/arxiv/2402.01354/
- __[Dynamic ML-GNN for Loan Risk Assessment](https://arxiv.org/abs/2402.00299)__: A dynamic multilayer network model has been created for improved credit risk assessment, considering borrower connections and their evolution over time. (2024-02-01, shares: 4) · https://www.ml-quant.com/papers/arxiv/2402.00299/
- __[Explainable AutoML for Credit Decisions](https://arxiv.org/abs/2402.03806)__: The use of Explainable Automated Machine Learning (AutoML) in financial engineering can improve the development of machine learning models for credit scoring and increase transparency in AI financial decisions. (2024-02-06, shares: 4) · https://www.ml-quant.com/papers/arxiv/2402.03806/
- __[Option Pricing for BNS Model](https://arxiv.org/abs/2402.00445)__: A supervised deep-learning scheme has been developed to accurately compute call option prices for the Barndorff-Nielsen and Shephard model, using an additional input variable from the Black-Scholes formula. (2024-02-01, shares: 3) · https://www.ml-quant.com/papers/arxiv/2402.00445/

### Miscellaneous

- __[QuantAgent: Enhanced Accuracy in Autonomous Trading](https://arxiv.org/abs/2402.03755)__: Enhanced Accuracy in Autonomous Trading: A new system allows autonomous agents using Large Language Models to effectively create and incorporate a specialized knowledge base, proven effective in quantitative investment. (2024-02-06, shares: 5) · https://www.ml-quant.com/papers/arxiv/2402.03755/
- __[Learning Market Dynamics with MARL](https://arxiv.org/abs/2402.00787)__: A new method is suggested for depicting diverse processing-limited agents in a multi-agent reinforcement learning system, showing enhanced predictive ability in multiple real-world situations. (2024-02-01, shares: 5) · https://www.ml-quant.com/papers/arxiv/2402.00787/
- __[TAC Method for Fitting Exponential Autoregressive Models in Economic Science](http://dx.doi.org/10.3390/math9080862)__: The study discusses the use of the TAC algorithm to solve approximation problems with exponential functions in economics, successfully applying it to various economic sectors. (2024-02-06, shares: 3) · https://www.ml-quant.com/papers/doi/10-3390-math9080862/
- __[Learning to Generate Explainable Stock Predictions with Large Language Models](https://arxiv.org/abs/2402.03659)__: The paper introduces the SEP framework, which uses a self-reflective agent and Proximal Policy Optimization to train Large Language Models for generating accurate and explainable stock predictions. (2024-02-06, shares: 3) · https://www.ml-quant.com/papers/arxiv/2402.03659/
- __[Securely Modeling Cyber Risk Based on Security Posture and Peer Comparison](https://arxiv.org/abs/2402.04166)__: The paper presents a new framework for comparing cyber risk and security within specific economic sectors, introducing the Defense Gap Index to predict an organization's security risk using historical industry data. (2024-02-06, shares: 3) · https://www.ml-quant.com/papers/arxiv/2402.04166/

### Crypto & Blockchain

- __[Future Contracts on CEXs and DEXs](https://arxiv.org/abs/2402.03953)__: The study analyzes trader behavior on perpetual future contracts in both centralized and decentralized exchanges, focusing on the impact of blockchain technology and the potential risks and benefits in the DeFi sector. (2024-02-06, shares: 9) · https://www.ml-quant.com/papers/arxiv/2402.03953/
- __[Sharing Longevity Risk in Heterogeneous Pools](https://arxiv.org/abs/2402.00855)__: The paper introduces a model for distributing income and benefits of longevity-risk pools among participants with different wealth and health statuses, tackling the issue of benefit allocation in smaller pools. (2024-02-01, shares: 4) · https://www.ml-quant.com/papers/arxiv/2402.00855/

### Historical Trending

- __[Smart Agent-Based Modeling for Competition and Collusion](https://arxiv.org/abs/2308.10974)__: The study presents Smart Agent-Based Modeling (SABM), a method using GPT-4 technologies to simulate human-like strategies and communication for studying firm competition and collusion. (2023-08-21, shares: 25) · https://www.ml-quant.com/papers/arxiv/2308.10974/
- __[Pricing American Put Options with Stochastic Interest Rate](https://arxiv.org/abs/2104.08502)__: The paper investigates the pricing of American put options in the Black and Scholes market with a stochastic interest rate, proving the existence of an optimal exercise boundary and providing a numerical study of the option price. (2021-04-17, shares: 24) · https://www.ml-quant.com/papers/arxiv/2104.08502/
- __[Optimal Liquidation with Asset Bubbles](https://arxiv.org/abs/2209.04001)__: The research uses a game-theoretic model to study optimal liquidation during an asset bubble, proving the existence of equilibria and analyzing the relationship between the bubble burst and equilibrium strategies. (2022-09-08, shares: 24) · https://www.ml-quant.com/papers/arxiv/2209.04001/
- __[Bayesian Theory of Market Impact on Large Orders](https://arxiv.org/abs/2303.08867)__: The research explains how large orders, split into smaller ones (meta-orders), affect prices in financial markets, suggesting that the square-root impact law originates from the over-estimation of order flows from meta-orders. (2023-03-15, shares: 19) · https://www.ml-quant.com/papers/arxiv/2303.08867/
- __[Deep Learning for Pair Trading](https://arxiv.org/abs/2401.14199)__: The MTRGL framework, which merges time series data and discrete features into a temporal graph, could improve automated pair trading strategies in finance. (2024-01-25, shares: 15) · https://www.ml-quant.com/papers/arxiv/2401.14199/
- __[Raising t-Statistic Hurdles](https://arxiv.org/abs/2204.10275)__: The study indicates that increasing statistical barriers to prevent false discoveries in academic papers may be unjustifiable due to bias in the published data. (2022-04-21, shares: 14) · https://www.ml-quant.com/papers/arxiv/2204.10275/
- __[Resilience to Cyber Contagion](http://arxiv.org/abs/2312.13884)__: A new type of risk measures has been developed to manage systemic risk in networks, focusing on the network's topological structure to reduce the spread risk of contagious threats. (2023-12-21, shares: 14) · https://www.ml-quant.com/papers/arxiv/2312.13884/

## SSRN

### Quantitative

- __[Financial Applications Using R Software](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4716425)__: The article discusses various Machine Learning techniques used in finance and offers advice on selecting methods for financial applications. (2024-02-04, shares: 5) · https://www.ml-quant.com/papers/ssrn/4716425/
- __[Risk Premium with Interpretable Machine Learning](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4714819)__: The research successfully incorporates the neural additive model into asset pricing, improving economic gains, prediction performance, and understanding of economic insight. (2024-02-02, shares: 3) · https://www.ml-quant.com/papers/ssrn/4714819/
- __[Economic Activity with Satellite Data and Neural Networks](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4712741)__: The study shows that using daily satellite images and machine learning to track economic activity is more effective than traditional models, particularly in the cement and construction industries. (2024-02-01, shares: 3) · https://www.ml-quant.com/papers/ssrn/4712741/
- __[European Asset Pricing with Generative AI](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4715376)__: The study questions traditional factor models in the European stock market, proposing an AI asset pricing model that considers a wider range of factors, indicating a more intricate risk-sharing mechanism. (2024-02-03, shares: 3) · https://www.ml-quant.com/papers/ssrn/4715376/
- __[Machine Learning for Value Investing in Credits](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4718484)__: The research introduces a new machine learning-based value factor for credit market investing, which performs better by capitalizing more on mispricings and less on risk. (2024-02-02, shares: 3) · https://www.ml-quant.com/papers/ssrn/4718484/
- __[Interval Estimation: Uncertain Models](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4712825)__: Uncertain Models: The paper introduces a new method to build interval estimators that account for misspecification uncertainty, showcasing its use in reevaluating the Capital Asset Pricing Model. (2022-03-28, shares: 2) · https://www.ml-quant.com/papers/ssrn/4712825/
- __[Risk Factor Disclosures: Materiality](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4718265)__: Materiality: The article introduces a new method to evaluate the significance of disclosed risks, discovering a decrease in significance among risk types following amendments to the Securities and Exchange Commission's rules. (2023-12-02, shares: 2) · https://www.ml-quant.com/papers/ssrn/4718265/
- __[Best Timing for Government Asset Purchases](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4717254)__: A study suggests that buying assets in normal times can lead to inefficient risk-taking, while selling assets can enhance risk sharing but may disrupt intertemporal smoothing, affecting the optimal management of public portfolios. (2023-02-10, shares: 2) · https://www.ml-quant.com/papers/ssrn/4717254/

### Financial

- __[Volatility Models: Pricing and Hedging with Fourier](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4714535)__: Pricing and Hedging with Fourier: The research investigates a volatility model incorporating famous models like SteinStein Bergomi and Heston, using Fourier inversion techniques for pricing and hedging certain options. (2024-02-02, shares: 171) · https://www.ml-quant.com/papers/ssrn/4714535/
- __[Asset Allocation Model for Semi-Active Investors](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4715415)__: The Pragmatic Asset Allocation strategy offers a balanced approach to asset allocation, providing a 10.73% annual return and a Sharpe ratio of 0.93. (2024-02-03, shares: 2) · https://www.ml-quant.com/papers/ssrn/4715415/
- __[Leveraged Trading on Lending Platforms](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4713126)__: The article compares loan positions on decentralized lending platforms with perpetual futures, finding less volatility in the implied funding fee/rate and a correlation between liquidations and margin closeouts. (2024-02-01, shares: 5) · https://www.ml-quant.com/papers/ssrn/4713126/
- __[Sparse Spanning Portfolios and Under-Diversification](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4713517)__: The study explores whether relaxing sparsity constraints on portfolios enhances investment opportunities, finding no benefit from expanding a sparse opportunity set beyond 45 assets. (2024-02-01, shares: 5) · https://www.ml-quant.com/papers/ssrn/4713517/
- __[Crude-Oil-Market Fundamentals from Futures Data](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4718895)__: The article emphasizes the importance of unbiased and accurate data in understanding crude oil market fundamentals through price relationship data. (2024-02-06, shares: 2) · https://www.ml-quant.com/papers/ssrn/4718895/
- __[Insider Trading Reporting and Profits](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4715160)__: The study shows that prompt reporting of insider trading, as enforced by the Sarbanes-Oxley Act of 2002, can enhance insider trading profits through improved coordination. (2024-02-02, shares: 3) · https://www.ml-quant.com/papers/ssrn/4715160/
- __[Market Quality in High Frequency Markets with Circuit Breakers](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4716722)__: The paper evaluates the efficacy of short-term circuit breakers in financial market regulation, finding that non-HFTs and mix-HFTs provide liquidity during trading halts, while HFTs engage in more aggressive trading. (2024-02-05, shares: 3) · https://www.ml-quant.com/papers/ssrn/4716722/
- __[ML and Expected Returns: Predictive Power](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4713982)__: Predictive Power: Machine learning models using option-based estimators are more effective than traditional models in predicting stock returns, especially for stocks with liquid options. (2023-02-02, shares: 2) · https://www.ml-quant.com/papers/ssrn/4713982/
- __[Interpretable ML for Creditor Recovery](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4716003)__: Interpretable machine learning methods excel over traditional models in finance, specifically in modeling corporate bond recovery rates. (2022-08-29, shares: 2) · https://www.ml-quant.com/papers/ssrn/4716003/
- __[TSMixer: Stock Volatility Forecasting with Neural Networks](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4713756)__: Stock Volatility Forecasting with Neural Networks: The TSMixer neural network model has proven to be more effective than traditional models in predicting stock market volatility, indicating a possible shift towards simpler models in the future. (2024-01-25, shares: 2) · https://www.ml-quant.com/papers/ssrn/4713756/
- __[Dynamic Currency Hedging with Non-Gaussianity](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4716896)__: A new currency hedging strategy for global investors, which takes into account investor ambiguity, has been introduced. (2021-08-19, shares: 2) · https://www.ml-quant.com/papers/ssrn/4716896/
- __[News Diffusion and Stock Market Reactions](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4717833)__: The spread of public news through social networks influences investors' beliefs and the securities market, with increased social connectivity leading to quicker news integration into prices but also causing differing opinions and excessive trading. (2021-04-12, shares: 2) · https://www.ml-quant.com/papers/ssrn/4717833/
- __[Money Anxiety Index: Equity Performance Prediction](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4716491)__: Equity Performance Prediction: The Money Anxiety Index has identified a group of ETFs that perform better than the market in both long and short positions, with performance not solely based on the risk control variable (Beta). (2023-11-29, shares: 2) · https://www.ml-quant.com/papers/ssrn/4716491/
- __[Cyber Risk and Stock Returns](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4716975)__: A machine learning algorithm that measures a firm's proximity to cyber risk outperforms traditional methods, with stocks at high cyber risk generating significant additional returns. (2023-10-31, shares: 2) · https://www.ml-quant.com/papers/ssrn/4716975/

## RePEc

### Finance

- __[Intraday Volatility and Return Link](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.mdpi.com%2F1911-8074%2F17%2F1%2F39%2Fpdf%3Bh%3Drepec%3Agam%3Ajjrfmx%3Av%3A17%3Ay%3A2024%3Ai%3A1%3Ap%3A39-%3Ad%3A1321582)__: The research uses the VIX method on individual equity options data, finding a negative correlation between stock returns and volatility, which is likely due to behavioral biases. (2024-02-07, shares: 29) · https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-1-p-39-d-1321582/
- __[Volatility and Equity Returns in South Africa](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.inderscience.com%2Flink.php%3Fid%3D136131%3Bh%3Drepec%3Aids%3Aafasfa%3Av%3A14%3Ay%3A2024%3Ai%3A1%3Ap%3A83-99)__: The research explores the connection between the South African volatility index and Johannesburg Stock Exchange listed stock indices, concluding that the TGARCH model is best for modeling volatility and the SAVI has a significant positive relationship with all selected indices. (2024-02-07, shares: 26) · https://www.ml-quant.com/papers/repec/ids-afasfa-v-14-y-2024-i-1-p-83-99/
- __[VIX and SPX Futures Lead-Lag Relationship](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS1386418123000496%3Bh%3Drepec%3Aeee%3Afinmar%3Av%3A67%3Ay%3A2024%3Ai%3Ac%3As1386418123000496)__: The study investigates the relationship between VIX futures and SPX futures, discovering a strong negative correlation when volatility is high, with VIX futures leading, and that market liquidity and hedging activities influence this relationship. (2024-02-07, shares: 20) · https://www.ml-quant.com/papers/repec/eee-finmar-v-67-y-2024-i-c-s1386418123000496/
- __[Opening Price Gaps and Information Adjustment in Stocks](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Flink.springer.com%2F10.1007%2Fs10614-023-10363-w%3Bh%3Drepec%3Akap%3Acompec%3Av%3A63%3Ay%3A2024%3Ai%3A2%3Ad%3A10.1007_s10614-023-10363-w)__: AI and big data research on gap opening price strategies show that negative gaps are more common than positive ones, and bad news adjusts prices faster than good news, with positive gaps offering profitable trading chances. (2024-02-07, shares: 11) · https://www.ml-quant.com/papers/repec/kap-compec-v-63-y-2024-i-2-d-10-1007-s10614-023-10363-w/
- __[Portfolio Vulnerability to Systemic Risk: A Vine Copula and APARCH-DCC Approach](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Flink.springer.com%2F10.1186%2Fs40854-023-00559-2%3Bh%3Drepec%3Aspr%3Afininn%3Av%3A10%3Ay%3A2024%3Ai%3A1%3Ad%3A10.1186_s40854-023-00559-2)__: A Vine Copula and APARCH-DCC Approach: A study on the systemic risk measure CoVaR found its estimates vary based on portfolio strategy, with higher values for cryptocurrency portfolios, highlighting CoVaR's usefulness in assessing portfolio systemic risk. (2024-02-07, shares: 10) · https://www.ml-quant.com/papers/repec/spr-fininn-v-10-y-2024-i-1-d-10-1186-s40854-023-00559-2/

### Statistical

- __[Predicting Commodity Futures Returns with ML](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdoi.org%2F10.1002%2Ffut.22471%3Bh%3Drepec%3Awly%3Ajfutmk%3Av%3A44%3Ay%3A2024%3Ai%3A2%3Ap%3A302-322)__: Machine learning can accurately predict future returns in commodities, with strategies based on these predictions outperforming traditional models. (2024-02-07, shares: 15) · https://www.ml-quant.com/papers/repec/wly-jfutmk-v-44-y-2024-i-2-p-302-322/
- __[Volatility Spillover and Forecasting in Stock Markets](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS1057521923004805%3Bh%3Drepec%3Aeee%3Afinana%3Av%3A91%3Ay%3A2024%3Ai%3Ac%3As1057521923004805)__: Volatility spillover across Shanghai, Hong Kong, and U.S. stock markets varies over time and regime, suggesting traditional forecast models could be improved by considering these factors. (2024-02-07, shares: 10) · https://www.ml-quant.com/papers/repec/eee-finana-v-91-y-2024-i-c-s1057521923004805/

### Machine Learning

- __[Crypto Market Analysis with ML](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F1351847X.2021.1908390%3Bh%3Drepec%3Ataf%3Aeurjfi%3Av%3A30%3Ay%3A2024%3Ai%3A1%3Ap%3A78-100)__: Researchers have created a machine learning model that can predict cryptocurrency market changes with 78% accuracy, proving that extensive data sequences aren't needed for accurate forecasts. (2024-02-07, shares: 25) · https://www.ml-quant.com/papers/repec/taf-eurjfi-v-30-y-2024-i-1-p-78-100/
- __[Dimensionality Reduction with Dynamics & ML](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS0378475423004883%3Bh%3Drepec%3Aeee%3Amatcom%3Av%3A218%3Ay%3A2024%3Ai%3Ac%3Ap%3A98-111)__: A new method that merges dynamical mechanisms and machine learning has been developed to simplify high-dimensional complex systems, demonstrating strong predictive capabilities even with noisy data. (2024-02-07, shares: 19) · https://www.ml-quant.com/papers/repec/eee-matcom-v-218-y-2024-i-c-p-98-111/
- __[ESG Ratings for Profitable Investments](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F20430795.2021.2013151%3Bh%3Drepec%3Ataf%3Ajsustf%3Av%3A14%3Ay%3A2024%3Ai%3A1%3Ap%3A184-198)__: Studies show a positive link between ESG (environment, social relations, and corporate governance) data and financial growth, with machine learning models providing more accurate predictions when both ESG and financial data are used. (2024-02-07, shares: 17) · https://www.ml-quant.com/papers/repec/taf-jsustf-v-14-y-2024-i-1-p-184-198/
- __[Gold Price Prediction with Hurst-based ML](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS0301420723011418%3Bh%3Drepec%3Aeee%3Ajrpoli%3Av%3A88%3Ay%3A2024%3Ai%3Ac%3As0301420723011418)__: A new hybrid model using machine learning and Hurst-oriented reconfiguration has been developed to predict gold prices more accurately than traditional models. (2024-02-07, shares: 16) · https://www.ml-quant.com/papers/repec/eee-jrpoli-v-88-y-2024-i-c-s0301420723011418/
- __[Active Learning for Ensemble Models](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.mdpi.com%2F2571-905X%2F7%2F1%2F8%2Fpdf%3Bh%3Drepec%3Agam%3Ajstats%3Av%3A7%3Ay%3A2024%3Ai%3A1%3Ap%3A8-137%3Ad%3A1325699)__: A new study introduces a framework that combines active learning with ensemble learning, showing that active learning can help the stacking model achieve similar accuracy to the SVM model with fewer instances. (2024-02-07, shares: 11) · https://www.ml-quant.com/papers/repec/gam-jstats-v-7-y-2024-i-1-p-8-137-d-1325699/
- __[Machine Learning Simplifies Finance in Real Time](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.cesifo.org%2FDocDL%2Fcesifo1_wp10909.pdf%3Bh%3Drepec%3Aces%3Aceswps%3A_10909)__: The article introduces a new deep learning algorithm designed to solve complex financial models. This algorithm provides new economic insights while keeping computational costs low. (2024-02-07, shares: 11) · https://www.ml-quant.com/papers/repec/ces-ceswps-10909/

### Historical Trending

- __[Machine Learning for Risk Measurement](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fhstalks.com%2Farticle%2F8214%2Fdownload%2F%3Bh%3Drepec%3Aaza%3Armfi00%3Ay%3A2023%3Av%3A17%3Ai%3A1%3Ap%3A43-52)__: A new algorithm based on Kalman filtering improves risk measurement in financial markets, outperforming traditional historical simulation methods. (2023-12-11, shares: 31) · https://www.ml-quant.com/papers/repec/aza-rmfi00-y-2023-v-17-i-1-p-43-52/
- __[Uncertainty and Exchange Rates](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fwww.emerald.com%2Finsight%2Fcontent%2Fdoi%2F10.1108%2FSEF-12-2022-0579%2Ffull%2Fhtml%3Futm_source%3Drepec%26utm_medium%3Dfeed%26utm_campaign%3Drepec%3Bh%3Drepec%3Aeme%3Asefpps%3Asef-12-2022-0579)__: Research shows that economic policy and global financial market uncertainties increase exchange rate volatility, while US monetary policy uncertainty reduces it. (2023-02-16, shares: 29) · https://www.ml-quant.com/papers/repec/eme-sefpps-sef-12-2022-0579/
- __[Interest Rate Volatility in Developing Countries](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdj.univ-danubius.ro%2Findex.php%2FAUDOE%2Farticle%2Fview%2F2374%2F2587%3Bh%3Drepec%3Adug%3Aactaec%3Ay%3A2023%3Ai%3A4%3Ap%3A176-192)__: A study reveals that interest rate volatility negatively affects financial stability in African Union countries, while money growth variations stabilize the sector. (2023-02-06, shares: 24) · https://www.ml-quant.com/papers/repec/dug-actaec-y-2023-i-4-p-176-192/
- __[Fractal Analysis for Portfolio Optimization](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F23322039.2023.2286755%3Bh%3Drepec%3Ataf%3Aoaefxx%3Av%3A11%3Ay%3A2023%3Ai%3A2%3Ap%3A2286755)__: Using a Hurst exponent index in portfolio optimization at the Damascus Securities Exchange results in portfolios that outperform the market in various metrics. (2023-07-10, shares: 23) · https://www.ml-quant.com/papers/repec/taf-oaefxx-v-11-y-2023-i-2-p-2286755/
- __[Asset Diversification in Volatile Markets](https://econpapers.repec.org/scripts/redir.pf?u=ftp%3A%2F%2Fw82.ranepa.ru%2Frnp%2Fsmmscn%2Fs23412.pdf%3Bh%3Drepec%3Arnp%3Asmmscn%3As23412)__: The article suggests optimizing the risk-return ratio of an investment portfolio by selecting suitable investment proportions for each asset using G. Markowitz's theory and Excel. (2023-09-24, shares: 21) · https://www.ml-quant.com/papers/repec/rnp-smmscn-s23412/
- __[Machine Learning for Landslide Susceptibility in Doboj City](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F17445647.2022.2163199%3Bh%3Drepec%3Ataf%3Atjomxx%3Av%3A19%3Ay%3A2023%3Ai%3A1%3Ap%3A2163199)__: A machine learning model was developed to assess landslide risks in Doboj City, achieving a 92% accuracy rate. (2023-02-24, shares: 16) · https://www.ml-quant.com/papers/repec/taf-tjomxx-v-19-y-2023-i-1-p-2163199/
- __[Macroeconomic Variables Impact on Exchange Rate Volatility in Turkey](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fcdn.istanbul.edu.tr%2Ffile%2FJTA6CLJ8T5%2FF25E7B01A32040A7B7C09D7B37D80B15%3Bh%3Drepec%3Aist%3Aekoist%3Av%3A0%3Ay%3A2023%3Ai%3A39%3Ap%3A49-64)__: A study found that in Turkey, exchange rate volatility has a more prolonged impact on inflation than on real GDP. (2023-02-08, shares: 16) · https://www.ml-quant.com/papers/repec/ist-ekoist-v-0-y-2023-i-39-p-49-64/
- __[Covariance Matrix Estimation with Empirical Bayes Method](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fjournals.sagepub.com%2Fdoi%2F10.1177%2F21582440231174777%3Bh%3Drepec%3Asae%3Asagope%3Av%3A13%3Ay%3A2023%3Ai%3A2%3Ap%3A21582440231174777)__: A method for improving covariance matrix estimation in portfolio analysis was presented, showing superior performance over existing methods. (2023-09-11, shares: 16) · https://www.ml-quant.com/papers/repec/sae-sagope-v-13-y-2023-i-2-p-21582440231174777/
- __[Oil, Gold, and China Stock Market Relationships](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.theibfr2.com%2FRePEc%2Fibf%2Fijbfre%2Fijbfr-v16n1-2022%2FIJBFR-V16N1-2022-3.pdf%3Bh%3Drepec%3Aibf%3Aijbfre%3Av%3A16%3Ay%3A2022%3Ai%3A1%3Ap%3A35-46)__: A study found that the Shanghai Securities Composite Index is influenced by international oil and gold prices, with a specific threshold effect identified for oil. (2022-03-10, shares: 14) · https://www.ml-quant.com/papers/repec/ibf-ijbfre-v-16-y-2022-i-1-p-35-46/
- __[ASEAN-4 Countries: Payment System Innovation and Financial System Stability](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.lpem.org%2Frepec%2Flpe%2Fefijnl%2F202209.pdf%3Bh%3Drepec%3Alpe%3Aefijnl%3A202209)__: Payment System Innovation and Financial System Stability: Research shows that enhancing payment system innovation in ASEAN countries reduces risks to financial system stability. (2022-01-22, shares: 13) · https://www.ml-quant.com/papers/repec/lpe-efijnl-202209/

## Machine learning

### Recently Published

- __[DeepSeekMath: Advancing Math Reasoning in Language Models](https://arxiv.org/abs/2402.03300)__: Advancing Math Reasoning in Language Models: DeepSeekMath7B is a new language model that uses web data and Group Relative Policy Optimization for advanced mathematical reasoning, scoring high on the MATH benchmark. (2024-02-05, shares: 127) · https://www.ml-quant.com/papers/arxiv/2402.03300/
- __[BootsTAP: Improving Tracking-Any-Point Models with Real-World Data](https://arxiv.org/abs/2402.00847)__: Improving Tracking-Any-Point Models with Real-World Data: A self-supervised student-teacher setup is presented to enhance a Tracking-Any-Point model using large-scale, unlabeled, real-world data, achieving top performance on the TAP-Vid benchmark. (2024-02-01, shares: 15) · https://www.ml-quant.com/papers/arxiv/2402.00847/
- __[NLP Research on Typological Diversity: NLP Research on Diversity](http://arxiv.org/abs/2402.04222)__: NLP Research on Diversity: The research explores 'typological diversity' in multilingual NLP studies, finding no clear definitions, and suggests future research should justify the diversity of language samples. (2024-02-06, shares: 14) · https://www.ml-quant.com/papers/arxiv/2402.04222/

### Historical Trending

- __[Self-Repair in Code Generation: Effectiveness](https://arxiv.org/pdf/2306.09896.pdf)__: Effectiveness: Large language models like CodeLlama, GPT-3.5, and GPT-4 show modest and inconsistent performance in self-repairing code, indicating limitations in self-feedback. (2023-06-16, shares: 530) · https://www.ml-quant.com/papers/arxiv/2306.09896/
- __[Extreme Compression of Language Models](https://arxiv.org/abs/2401.06118)__: The article discusses a new algorithm that enhances the compression of large language models, providing better accuracy and is now available for future research. (2024-01-11, shares: 45) · https://www.ml-quant.com/papers/arxiv/2401.06118/
- __[DSPy Assertions: Constraints for Language Model Pipelines](http://arxiv.org/abs/2312.13382)__: Constraints for Language Model Pipelines: The article introduces LM Assertions, a new programming construct that enhances rule compliance and task performance in text generation by expressing computational constraints in language models. (2023-12-20, shares: 41) · https://www.ml-quant.com/papers/arxiv/2312.13382/

## Papers with code

### Trending

- __[Language Model Revolutionizes Code Intelligence](https://github.com/deepseek-ai/DeepSeek-Coder)__: Advanced code intelligence in software development has been significantly improved by large language models. (2024-02-02, shares: 4230)
- __[Dolma: Open Corpus for LM Pretraining Research](https://github.com/allenai/dolma)__: Open Corpus for LM Pretraining Research: The article points out the insufficient details provided about the creation of top-performing language models, despite their importance in natural language processing tasks. (2024-02-04, shares: 451)
- __[Nomic Embed: Reproducible Long Context Text Embedder](https://github.com/nomic-ai/contrastors)__: Reproducible Long Context Text Embedder: The article details the training of nomicembedtextv1, the first fully reproducible, open-source English text embedding model that surpasses both OpenAI Ada002 and OpenAI textembedding3small in short and long-context tasks. (2024-02-06, shares: 232)

### Rising

- __[Survey on Large Models for Time Series and SpatioTemporal Data](https://github.com/kimmeen/time-llm)__: The survey provides an extensive review of large models for time series and spatiotemporal data, discussing data types, model categories, scopes, and applications. (2024-02-02, shares: 67)
- __[HiSAM: Hierarchical Text Segmentation Model](https://github.com/ymy-k/hi-sam)__: Hierarchical Text Segmentation Model: The article details the process of HiSAM in AMG mode, which includes segmenting text stroke foreground masks and sampling foreground points for hierarchical text mask generation, to achieve layout analysis. (2024-02-03, shares: 41)

## GitHub

### Finance

- __[MultiFactor Backtesting Framework](https://github.com/etccapital/MultiFactor)__: The article explains the development of a MultiFactor Backtesting Framework, based on a report from Huatai Securities, a leading Chinese financial engineering firm. (2021-10-24, shares: 36)
- __[High-Frequency Arbitrage](https://github.com/bradleyboyuyang/Statistical-Arbitrage)__: The article explores the concept and use of high-frequency statistical arbitrage in financial markets. (2022-12-23, shares: 62)
- __[OLMo: Modeling & Inference Code](https://github.com/allenai/OLMo)__: Modeling & Inference Code: The article details the modeling, training, evaluation, and inference code for OLMo, a machine learning model. (2023-02-20, shares: 888)
- __[Improving Data for LLMs with Lilac](https://github.com/lilacai/lilac)__: The article highlights the necessity of gathering high-quality data for Language Models (LLMs). (2023-03-23, shares: 623)
- __[StarRocks: Next-Gen MPP OLAP Database](https://github.com/StarRocks/starrocks)__: Next-Gen MPP OLAP Database: The article presents StarRocks, a Linux Foundation project and next-gen MPP OLAP database, which received InfoWorld’s 2023 BOSSIE Award for best open source software. (2021-09-04, shares: 7225)

### Trending

- __[StableIdentity: Anybody Anywhere](https://github.com/qinghew/StableIdentity)__: Anybody Anywhere: StableIdentity introduces a technology for instant and seamless placement of individuals in any location. (2024-01-30, shares: 101)
- __[lightninghydratemplate: Userfriendly ML](https://github.com/ashleve/lightning-hydra-template)__: Userfriendly ML: PyTorch Lightning Hydra offers a simplified template for conducting machine learning experiments. (2020-11-04, shares: 3375)
- __[MiniCPM2B: Endside LLM Outperforms Llama213B](https://github.com/OpenBMB/MiniCPM)__: Endside LLM Outperforms Llama213B: MiniCPM2B, an endside LLM, outperforms Llama213B in terms of performance. (2024-01-29, shares: 1135)
- __[mergekit: Language Model Merging Tools](https://github.com/arcee-ai/mergekit)__: Language Model Merging Tools: The article presents tools for incorporating pre-trained large language models. (2023-08-21, shares: 1991)

## News

- __[Quant Equity Strategies: A Fundamental View -> Quant Equity Strategies: Fundamental View](https://www.flirtingwithmodels.com/2024/02/05/s7e5-a-fundamental-view-of-quant-equity/)__: A Fundamental View -> Quant Equity Strategies: Fundamental View: Clayton Gillespie emphasizes the need to blend fundamental understanding with quantitative equity strategies, highlighting potential conflicts between fundamental and statistical interpretations. (2024-02-05, shares: 10)
- __[Vanguard Quietly Adopts AI in $13B Quant Stock Funds](https://news.google.com/rss/articles/CBMicmh0dHBzOi8vd3d3LmJsb29tYmVyZy5jb20vbmV3cy9hcnRpY2xlcy8yMDI0LTAyLTA2L3Zhbmd1YXJkLXF1aWV0bHktZW1icmFjZXMtYWktaW4tMTMtYmlsbGlvbi1vZi1xdWFudC1zdG9jay1mdW5kc9IBAA?oc=5)__: Vanguard is discreetly integrating AI into $13 billion of its quant stock funds, as reported by Bloomberg. (2024-02-06, shares: 2)

## Videos

### Quantitative

- __[Risk Comp](https://www.youtube.com/watch?v=VuP7nx_d5_Y)__: The 2022 Selby Jennings risk report offers a detailed look at the salary and career growth of banking quants in different financial hubs. (2024-02-04, shares: 43)
- __[Finance Quants](https://www.youtube.com/watch?v=3soVbJpRmgA)__: The split of financial engineering from finance has increased job prospects, however, financial engineers are not highly favored in business schools. (2024-02-06, shares: 6)
- __[CQF Cert](https://www.youtube.com/watch?v=c5c3HQPhH_I)__: The article provides information about the CQF certification in the field of quantitative finance. (2024-02-01, shares: 8)
- __[Success in Quant Finance](https://www.youtube.com/watch?v=PbUI9GRMgfE)__: The Corporate Chat McGill Podcast, available on all major podcast platforms, includes an in-depth interview. (2024-02-05, shares: 2)

## X / Twitter

### Quantitative

- __[Machine Learning in Finance](https://twitter.com/quantseeker/status/1753804479999135751)__: The article reviews recent studies on the use of machine learning in asset pricing and corporate finance. (2024-02-03, shares: 11)
- __[Advanced Portfolio Optimization and Machine Learning in Asset Management](https://twitter.com/carlcarrie/status/1753767434425708706)__: Amundis Thierry Roncalli discusses portfolio optimization, climate and ESG portfolio building, and the role of machine learning in asset management. (2024-02-03, shares: 9)
- __[SABR Model for Options Trading](https://twitter.com/carlcarrie/status/1753384522152886277)__: The article offers a guide and Python code for using the SABR stochastic volatility model in options trading. (2024-02-02, shares: 6)
- __[No Systemic Risks in 0DTE Options](https://twitter.com/quantseeker/status/1754546073010328028)__: A recent study dismisses media claims that 0DTE options could pose systemic risks to the underlying market. (2024-02-05, shares: 2)

### Miscellaneous

- __[Equityfactor value by Zhang](https://twitter.com/quantseeker/status/1755190471758848236)__: Zhang's paper determines equity factor value by comparing the spread between long and short leg of factors, stating positive returns only occur when the spread surpasses the historical median. (2024-02-07, shares: 0)
- __[Autoregressive transformers predict tokens](https://twitter.com/carlcarrie/status/1754301493887299751)__: Mobile ALOHA, an open-source robot capable of performing complex tasks like cooking shrimp, using an elevator, and storing items, has been unveiled with 50 demonstrations. (2024-02-05, shares: 0)
- __[Codeempirical blog on token prediction in LLMs](https://twitter.com/carlcarrie/status/1754301045906280633)__: The blog post offers an empirical explanation on the effectiveness of autoregressive transformers in Language Model (LLMs) in predicting tokens. (2024-02-05, shares: 0)