---
title: Quant Letter No. 35: January 2024, Week 5
url: https://www.ml-quant.com/issues/2024-01-30/
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: 2024-01-30
---


# Quant Letter No. 35: January 2024, Week 5

Sent 2024-01-30. 71 items.

## arXiv

### Finance

- __[Pathwise XVA Computations with Explicit Scheme](https://arxiv.org/abs/2401.13314)__: A new simulation/regression scheme for a type of anticipated BSDEs is introduced, using neural network least-squares and quantile regressions, showing better results in high-dimensional and hybrid market/default risks XVA use-case. (2024-01-24, shares: 8) · https://www.ml-quant.com/papers/arxiv/2401.13314/
- __[Optimal Portfolio with Ratio-Type Periodic Evaluation](http://arxiv.org/abs/2401.14672)__: A study on portfolio management in an incomplete market model, where the portfolio's performance is periodically evaluated, confirms the existence of optimal portfolio processes and identifies the least favorable market completion. (2024-01-26, shares: 8) · https://www.ml-quant.com/papers/arxiv/2401.14672/
- __[FDR-Optimized Sparse Financial Index Tracking](https://arxiv.org/abs/2401.15139)__: A new method for selecting important variables in complex data analysis, such as financial index tracking, has been developed, which manages the rate of false discoveries and handles groups of highly related variables. (2024-01-26, shares: 10) · https://www.ml-quant.com/papers/arxiv/2401.15139/
- __[Cash Non-Additive Risk Measures: Horizon Risk & Generalized Entropy](http://arxiv.org/abs/2401.14443)__: Horizon Risk & Generalized Entropy: A new risk measure based on generalized Tsallis entropy is introduced, which can dynamically assess the risk of losses considering both horizon risk and interest rate uncertainty, and can be used to quantify capital requirement. (2024-01-25, shares: 7) · https://www.ml-quant.com/papers/arxiv/2401.14443/
- __[Analysis of Aggregate Loss Model in Markov Renewal Regime](http://arxiv.org/abs/2401.14553)__: A model considering aggregate loss with dependent losses is studied, showing that considering the dependence and overdispersion in the inter-losses times distribution results in higher capital charges. (2024-01-25, shares: 6) · https://www.ml-quant.com/papers/arxiv/2401.14553/
- __[SOFR Futures Pricing](https://arxiv.org/abs/2401.15728)__: The article presents a pricing formula for SOFR futures contracts, taking into account intrinsic convexity adjustments and skew and smile from options markets. (2024-01-28, shares: 6) · https://www.ml-quant.com/papers/arxiv/2401.15728/
- __[ESG Pairs Algorithm for Sustainable Trading](http://arxiv.org/abs/2401.14761)__: The paper suggests an algorithmic trading strategy that combines ESG ratings with pairs trading, resulting in positive returns and adherence to ESG principles. (2024-01-26, shares: 6) · https://www.ml-quant.com/papers/arxiv/2401.14761/
- __[Flexible Residual Distribution in Hawkes Process](https://arxiv.org/abs/2401.13890)__: The article proposes a new model that enhances the Hawkes process in a discrete sense, allowing for the inclusion of various residual distributions for a more precise historical simulation. (2024-01-25, shares: 5) · https://www.ml-quant.com/papers/arxiv/2401.13890/
- __[Higher Order Option Price Approximation in Barndorff-Nielsen Models](https://arxiv.org/abs/2401.14390)__: The paper introduces an approximation method for pricing European options in Barndorff-Nielsen and Shephard models, utilizing a recursive algorithm for closed form option price approximations. (2024-01-25, shares: 5) · https://www.ml-quant.com/papers/arxiv/2401.14390/
- __[General Simulation of Lévy-driven OU Processes for Energy](https://arxiv.org/abs/2401.15483)__: The article presents a new simulation technique for Lévy-driven Ornstein-Uhlenbeck processes, providing a quicker and more precise method for pricing energy derivatives. (2024-01-27, shares: 5) · https://www.ml-quant.com/papers/arxiv/2401.15483/

### Miscellaneous

- __[MTRGL: Temporal Correlation Discerning](https://arxiv.org/abs/2401.14199)__: Temporal Correlation Discerning: The paper introduces a new framework, Multi-modal Temporal Relation Graph Learning (MTRGL), that merges time series data and discrete features to improve automated pair trading strategies. (2024-01-25, shares: 7) · https://www.ml-quant.com/papers/arxiv/2401.14199/
- __[Estimating Pareto's Scale Parameter from Grouped Data](http://arxiv.org/abs/2401.14593)__: The article presents a new technique called Method of Truncated Moments (MTuM) for estimating the tail index of a Pareto distribution from grouped data. (2024-01-26, shares: 12) · https://www.ml-quant.com/papers/arxiv/2401.14593/
- __[Functional Data Analysis for Stochastic Evolution Equations](https://arxiv.org/abs/2401.16286)__: The article presents a theory for estimating the continuous quadratic covariation of the latent random driver in stochastic evolution equations, using functional data analysis. (2024-01-29, shares: 5) · https://www.ml-quant.com/papers/arxiv/2401.16286/
- __[Determinants of Mode Choice Evaluation with Statistical and ML Models](http://arxiv.org/abs/2401.13977)__: The research examines mode choice decision making behavior using a Multinomial logit model and machine learning classifiers, and employs modern interpretability techniques to explain the decision making behavior. (2024-01-25, shares: 5) · https://www.ml-quant.com/papers/arxiv/2401.13977/

### Historical Trending

- __[Deep Calibration for Volatility Smile](https://arxiv.org/abs/2310.16703)__: The introduction of a Derivative-Constrained Neural Network (DCNN) enhances the calibration of implied volatility surface in option prices, aiding in understanding market dynamics and risk management. (2023-10-25, shares: 17) · https://www.ml-quant.com/papers/arxiv/2310.16703/
- __[Reducing Investment Risks](https://arxiv.org/abs/2304.11043)__: The Split Variational Adversarial Training (SVAT) method has been introduced for risk-aware stock recommendations, reducing investment risks and increasing risk-adjusted profits by over 30%. (2023-04-20, shares: 13) · https://www.ml-quant.com/papers/arxiv/2304.11043/
- __[Gender and Family Responsibilities](http://dx.doi.org/10.1080/09585192.2018.1505762)__: Research on the Spanish banking sector shows that work-family policies indirectly improve job performance through generated well-being, with no significant influence from gender or family responsibilities. (2023-12-12, shares: 12) · https://www.ml-quant.com/papers/doi/10-1080-09585192-2018-1505762/
- __[Stability of Fourth-Order Schemes](https://arxiv.org/abs/2209.02873)__: A study introduces fourth-order accurate compact schemes for variable coefficient convection diffusion equations, providing stability conditions and proving unconditional stability for constant coefficient problems. (2022-09-07, shares: 10) · https://www.ml-quant.com/papers/arxiv/2209.02873/
- __[Epistemic Limits of Causal Reductionism](https://arxiv.org/abs/2311.16570)__: A research paper suggests that the use of unidirectional causation in capital market studies may be flawed, and a better understanding of empirical finance could be achieved by recognizing the limitations of current quantitative finance tools. (2023-11-28, shares: 10) · https://www.ml-quant.com/papers/arxiv/2311.16570/

## SSRN

### Quantitative

- __[RL for Hedging Portfolios with Structured Products](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4709441)__: A new method of distributional reinforcement learning is suggested for managing portfolios with complex products like Autocallable notes, which are difficult to handle with traditional reinforcement learning due to their complexity. (2024-01-29, shares: 2) · https://www.ml-quant.com/papers/ssrn/4709441/
- __[Futures Markets' Impact on Currency Variance Forecasts in Asian Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4704913)__: The volatility of currency markets has become harder to predict with the introduction of futures, with machine learning models performing better than GARCH models, and simple historical volatility forecasts surpassing both. (2024-01-24, shares: 2) · https://www.ml-quant.com/papers/ssrn/4704913/
- __[Hybrid Random Projection for Enhanced High-Dimensional Data Representation](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4705621)__: A novel hybrid random projection method, HBP, merges the benefits of normal random projection and plus-minus one random projection, enhancing data dimension reduction while maintaining data structure. (2024-01-24, shares: 6) · https://www.ml-quant.com/papers/ssrn/4705621/
- __[Model Calibration vs Accuracy in ML for Sports Betting](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4705918)__: In sports betting, model calibration is found to be more crucial than accuracy in predicting outcomes, with calibration-based models yielding higher returns on investment. (2024-01-25, shares: 3) · https://www.ml-quant.com/papers/ssrn/4705918/
- __[Sentiment Trading with Language Models](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4706629)__: Large language models like OPT, based on GPT-3, are highly effective in predicting sentiment in U.S. financial news, impacting financial analysis tools and regulatory considerations. (2024-01-25, shares: 11) · https://www.ml-quant.com/papers/ssrn/4706629/
- __[Observable vs Latent Markov Chains for Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4706972)__: The latent-regime Betat-EGARCH model outperforms the observable-regime Betat-EGARCH model in in-sample statistical performance, but their out-of-sample density forecasting performances are similar. (2024-01-25, shares: 3) · https://www.ml-quant.com/papers/ssrn/4706972/
- __[Asset Pricing Primer for Big Data](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4707383)__: The lecture notes discuss Big Data Asset Pricing, covering topics like state prices, beta pricing, market efficiency, and factor models. (2022-04-29, shares: 2) · https://www.ml-quant.com/papers/ssrn/4707383/
- __[NFT Market Investor Sentiment Proxies](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708404)__: Google Trend affects the NFT market during bear markets, while Fear and Greed Index and Volatility Index impact it during bull markets, according to a study. (2022-06-08, shares: 2) · https://www.ml-quant.com/papers/ssrn/4708404/
- __[Identifying M&A Targets from Textual Disclosures](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4707567)__: Textual information from firm disclosures, analyzed using a transformer neural network, can significantly enhance the predictability of corporate takeovers, a study reveals. (2023-03-04, shares: 2) · https://www.ml-quant.com/papers/ssrn/4707567/

### Financial

- __[Social Media Sentiment & Crypto Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4706410)__: The paper explores the correlation between cryptocurrency market trends and investor sentiment, revealing a significant connection, especially influenced by large-scale investors. (2024-01-25, shares: 28) · https://www.ml-quant.com/papers/ssrn/4706410/
- __[Short Sellers' Behavior in Trading Halts](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4709469)__: The research looks into short selling activity during trading halts, discovering that short sellers significantly alter their behavior during these times, enhancing the understanding of the impact of short sales and trading halts. (2024-01-28, shares: 2) · https://www.ml-quant.com/papers/ssrn/4709469/
- __[High-Frequency Trading & Stock Price Crash Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4705469)__: High Frequency Trading (HFT) increases the risk of stock price crashes by over 80%, especially in larger firms, due to increased liquidity and less informative stock prices. (2024-01-24, shares: 2) · https://www.ml-quant.com/papers/ssrn/4705469/
- __[Uninformed Retail Investors & Capital Market Effects](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4705049)__: Uninformed trading, especially by less knowledgeable retail investors, negatively affects market liquidity and increases capital costs for smaller firms. (2024-01-24, shares: 2) · https://www.ml-quant.com/papers/ssrn/4705049/
- __[Correlated Demand Shocks & Asset Pricing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4705500)__: The correlated demand shocks from institutional investors can increase risk in asset pricing, with stocks exposed to higher correlated demand showing higher market betas and risk premiums. (2024-01-24, shares: 3) · https://www.ml-quant.com/papers/ssrn/4705500/
- __[Media Sentiment & Market Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4709058)__: Financial markets can experience volatility due to media sentiment, especially during significant events, and this impact can affect other markets as well. (2023-11-08, shares: 3) · https://www.ml-quant.com/papers/ssrn/4709058/
- __[Anomalies as Hedge Fund Factors](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4709472)__: A nine-factor model, which includes five anomaly factors, is effective in explaining hedge fund returns, highlighting the need for regular factor updates in the hedge fund sector. (2023-01-10, shares: 3) · https://www.ml-quant.com/papers/ssrn/4709472/
- __[ML Predicts Stock Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708642)__: Machine learning algorithms, especially neural networks, can predict stock return volatility using accounting-based characteristics, with profitability-related traits being the most predictive. (2021-11-24, shares: 2) · https://www.ml-quant.com/papers/ssrn/4708642/
- __[Smoothing Volatility-Managed Portfolios](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708509)__: Using a new variational Bayes inference method to smooth volatility forecasts can decrease excess leverage and turnover, thereby enhancing the performance of volatility-managed portfolios. (2022-12-27, shares: 2) · https://www.ml-quant.com/papers/ssrn/4708509/
- __[Mutual Fund Style-Shifting Skill](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708402)__: Most mutual funds use multiple investment styles, and those that change styles not only identify superior new styles but also surpass the benchmarks related to these new styles. (2023-10-27, shares: 2) · https://www.ml-quant.com/papers/ssrn/4708402/
- __[Efficiency Principles for Active Portfolio Selection](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4709083)__: The paper introduces a new ABL allocation model that merges subjective allocation rule and minimum tracking error to enhance portfolio performance and risk management. (2022-09-16, shares: 2) · https://www.ml-quant.com/papers/ssrn/4709083/
- __[Reinforcement Learning for Arbitrage in Decentralized Exchanges](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708173)__: The article presents a game-theory model to explain the tactics of various players in decentralized exchanges with automated market makers. (2023-12-20, shares: 2) · https://www.ml-quant.com/papers/ssrn/4708173/
- __[Enhancing Returns with Information in Currency Momentum Portfolios](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4709606)__: The study recommends conditional currency momentum strategies that use market data to boost the performance of currency momentum portfolios, which have been unprofitable since the financial crisis. (2023-04-17, shares: 2) · https://www.ml-quant.com/papers/ssrn/4709606/
- __[Financial Stability vs. Politics in Third-Country Central Counterparties](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4704566)__: The article explores the legal regulations governing the access of central counterparties to EU financial markets, including the recognition process for CCPs from non-EU countries. (2023-10-24, shares: 2) · https://www.ml-quant.com/papers/ssrn/4704566/
- __[Evidence and Profitable Strategies in Linear Asset Pricing Models](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4704766)__: The author suggests a new measure of mispricing in asset pricing models, providing evidence of mispricing in U.S. equity data and proposing a profitable investment strategy based on this mispricing. (2023-12-10, shares: 2) · https://www.ml-quant.com/papers/ssrn/4704766/

## RePEc

### Finance

- __[Intraday Volatility and Return Relationship](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 study uses the VIX method on individual equity options data, finding a negative correlation between stock returns and volatility, indicating behavioral biases. (2024-01-30, shares: 29) · https://www.ml-quant.com/papers/repec/gam-jjrfmx-v-17-y-2024-i-1-p-39-d-1321582/
- __[Factor Models in Portfolio Allocation: Hou-Xue-Zhang vs Fama-French](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS0261560623001985%3Bh%3Drepec%3Aeee%3Ajimfin%3Av%3A140%3Ay%3A2024%3Ai%3Ac%3As0261560623001985)__: Hou-Xue-Zhang vs Fama-French: The Hou-Xue-Zhang four-factor model slightly outperforms the Fama-French five-factor model in investments, unless margin requirements and model uncertainty are factored in. (2024-01-30, shares: 12) · https://www.ml-quant.com/papers/repec/eee-jimfin-v-140-y-2024-i-c-s0261560623001985/
- __[Estimating Dynamic Covariance Matrices: A Review](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS2452306221000587%3Bh%3Drepec%3Aeee%3Aecosta%3Av%3A29%3Ay%3A2024%3Ai%3Ac%3Ap%3A16-30)__: A Review: The article discusses recent advancements in estimating large dynamic covariance matrices, with a focus on GARCH model extensions, non- and semi-parametric models, and structural break detection. (2024-01-30, shares: 12) · https://www.ml-quant.com/papers/repec/eee-ecosta-v-29-y-2024-i-c-p-16-30/
- __[Mean-Variance Optimization with Affine GARCH](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.sciencedirect.com%2Fscience%2Farticle%2Fpii%2FS1544612323011212%3Bh%3Drepec%3Aeee%3Afinlet%3Av%3A59%3Ay%3A2024%3Ai%3Ac%3As1544612323011212)__: The use of Affine GARCH models in portfolio optimization is explored, showing superior performance over homoscedastic variants when used with S&P 500 market data. (2024-01-30, shares: 11) · https://www.ml-quant.com/papers/repec/eee-finlet-v-59-y-2024-i-c-s1544612323011212/
- __[Portfolio Vulnerability to Systemic Risk: 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)__: Vine Copula and APARCH-DCC Approach: The study assesses the sensitivity and robustness of the Conditional Value-at-Risk (CoVaR) systemic risk measure, finding that CoVaR estimates vary with portfolio strategy and are especially high for cryptocurrency portfolios. (2024-01-30, shares: 10) · https://www.ml-quant.com/papers/repec/spr-fininn-v-10-y-2024-i-1-d-10-1186-s40854-023-00559-2/

### Machine Learning

- __[Crypto Price Formation 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)__: Machine learning can accurately predict cryptocurrency market trends by 78%, with general features being more effective than asset-specific ones. (2024-01-30, shares: 25) · https://www.ml-quant.com/papers/repec/taf-eurjfi-v-30-y-2024-i-1-p-78-100/
- __[ESG Ratings for Investment Decisions](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)__: Profitable investments can be made by incorporating environmental, social, and corporate governance (ESG) data points, as high ESG scoring companies perform better financially. (2024-01-30, shares: 17) · https://www.ml-quant.com/papers/repec/taf-jsustf-v-14-y-2024-i-1-p-184-198/
- __[Identifying Politically Connected Firms with ML](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdoi.org%2F10.1111%2Fobes.12586%3Bh%3Drepec%3Abla%3Aobuest%3Av%3A86%3Ay%3A2024%3Ai%3A1%3Ap%3A137-155)__: Machine learning can identify over 85% of politically connected firms using financial and industry indicators, aiding in detecting conflicts of interest. (2024-01-30, shares: 14) · https://www.ml-quant.com/papers/repec/bla-obuest-v-86-y-2024-i-1-p-137-155/
- __[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)__: Active learning within ensemble learning can achieve similar predictive performance on a limited budget, with boosting or stacking models outperforming the SVM model when using the same uncertainty sampling. (2024-01-30, shares: 11) · https://www.ml-quant.com/papers/repec/gam-jstats-v-7-y-2024-i-1-p-8-137-d-1325699/

## Machine learning

### Recently Published

- __[Denoising Diffusion Models for Self-Supervised Learning](https://arxiv.org/abs/2401.14404)__: The study investigates Denoising Diffusion Models (DDM) and their ability to learn representations, suggesting a simplified approach similar to a Denoising Autoencoder (DAE). (2024-01-25, shares: 114) · https://www.ml-quant.com/papers/arxiv/2401.14404/
- __[Patch Dependence for Masked Autoencoders](https://arxiv.org/abs/2401.14391)__: The research proposes a new pretraining framework, Cross-Attention Masked Autoencoders (CrossMAE), which performs as well as Masked Autoencoders (MAE) but with less decoding computation. (2024-01-25, shares: 98) · https://www.ml-quant.com/papers/arxiv/2401.14391/
- __[Evaluating Multimodal Agents on Realistic Visual Web Tasks](https://arxiv.org/abs/2401.13649)__: VisualWebArena, a benchmark for assessing the performance of multimodal web agents on visually grounded tasks, is introduced, highlighting gaps in current multimodal language agents. (2024-01-24, shares: 56) · https://www.ml-quant.com/papers/arxiv/2401.13649/
- __[SliceGPT: Compressing Language Models](https://arxiv.org/abs/2401.15024)__: Compressing Language Models: The paper introduces SliceGPT, a post-training sparsification scheme for large language models that reduces the network's embedding dimension, maintains high performance, reduces inference computation, and reveals computational invariance in transformer networks. (2024-01-26, shares: 20) · https://www.ml-quant.com/papers/arxiv/2401.15024/
- __[Generalization of Overfitted DNNs in Adversarial Training](http://arxiv.org/abs/2401.13624)__: The study offers a theoretical insight into the robust overfitting issue in adversarial training on over-parameterized deep neural networks (DNNs), showing that overfitting can be avoided and a robust generalization gap is unavoidable, with the model capacity requirement depending on the target function's smoothness. (2024-01-24, shares: 19) · https://www.ml-quant.com/papers/arxiv/2401.13624/

## GitHub

### Finance

- __[Testing Market Trading Systems](https://github.com/Apress/testing-and-tuning-market-trading-systems)__: Timothy Masters shares source code to help test and optimize market trading systems. (2018-10-15, shares: 42)
- __[PandoraTrader: C Trade Platform](https://github.com/pegasusTrader/PandoraTrader)__: C Trade Platform: C Trade Platform provides a platform for developers to conduct high-frequency quantitative trading. (2019-01-03, shares: 733)
- __[Google Indexing Script](https://github.com/goenning/google-indexing-script)__: A new script can help get your website indexed on Google in less than two days. (2024-01-21, shares: 3816)
- __[Unleashing Large-Scale Unlabeled Data](https://github.com/LiheYoung/Depth-Anything)__: Depth Anything is investigating the possibilities of utilizing large-scale unlabeled data. (2024-01-22, shares: 3313)

### Trending

- __[BentoML: AI App Builder](https://github.com/bentoml/BentoML)__: AI App Builder: The article offers guidance on creating top-notch AI applications for business purposes. (2019-04-02, shares: 6192)
- __[Visualize Autogen Workforce with ide](https://github.com/xforceai/ide)__: The article details the process of visualizing autogen workforce creation through diagrams. (2023-12-27, shares: 142)
- __[Ollama Python Library: Simplified](https://github.com/ollama/ollama-python)__: Simplified: The article presents the Ollama Python library and its various features. (2023-12-09, shares: 462)
- __[OpenGFW: Easy GFW Implementation](https://github.com/apernet/OpenGFW)__: Easy GFW Implementation: The article explores OpenGFW, a user-friendly, open-source version of GFW for Linux. (2023-12-13, shares: 4545)
- __[Get Started with Llama 2 Mistral](https://github.com/ollama/ollama)__: The article provides a tutorial on installing and utilizing Llama 2 Mistral and other large language models locally. (2023-06-26, shares: 32998)

## X / Twitter

### Quantitative

- __[Timing Commodity Factors in Short-Term Factor Momentum](https://twitter.com/quantseeker/status/1752313437579800751)__: Researchers have found evidence of short-term factor momentum in commodity markets, suggesting possibilities for timing commodity factors. (2024-01-30, shares: 1)
- __[Portfolio Shrinkage Method for Novels](https://twitter.com/quantseeker/status/1752094257274388778)__: Article: The article introduces a new method for managing portfolios with more assets than observations, highlighting the role of low in-sample variance principal components in model performance. (2024-01-29, shares: 0)
- __[Commodity-Linked Currencies' Predictability](https://twitter.com/quantseeker/status/1751677941031874671)__: Article: The study identifies currencies positively affected by commodity prices, noting significant return predictability from past changes in commodity export prices, particularly in emerging market currencies during high FX volatility. (2024-01-28, shares: 0)
- __[Exotic Currencies' Strong Carry Returns](https://twitter.com/quantseeker/status/1751528322746454413)__: Article: The paper reveals that despite weaker FX carry returns among G10 currencies after the Global Financial Crisis, carry returns remain robust among exotic currencies, even after considering transaction costs. (2024-01-28, shares: 0)
- __[Language Models Beat Dictionary Models in Return Prediction](https://twitter.com/quantseeker/status/1750825993848135928)__: Article: The article shows that large language models trained on news are more effective than traditional dictionary models in predicting returns, with complex models like OPT having the highest predictability. (2024-01-26, shares: 0)