---
title: Quant Letter No. 43: April 2024, Week 1
url: https://www.ml-quant.com/issues/2024-04-03/
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: 2024-04-03
---


# Quant Letter No. 43: April 2024, Week 1

Sent 2024-04-03. 65 items.

## arXiv

### Finance

- __[Neural Networks for Finance](https://arxiv.org/abs/2404.01866)__: The study investigates the use of supervised autoencoders in improving financial forecasting through precise parameter tuning. (2024-04-02, shares: 3) · https://www.ml-quant.com/papers/arxiv/2404.01866/
- __[RL Agents in Market Simulation](https://arxiv.org/abs/2403.19781)__: The research introduces a market simulation framework using reinforcement learning agents that can mimic real-world market dynamics and adapt to major market events. (2024-03-28, shares: 2) · https://www.ml-quant.com/papers/arxiv/2403.19781/
- __[Curb Appeal with Deep Learning](https://arxiv.org/abs/2403.19915)__: Incorporating image data into econometric models through deep learning enhances the accuracy of residential real estate price predictions. (2024-03-29, shares: 4) · https://www.ml-quant.com/papers/arxiv/2403.19915/
- __[Optimal Rebalancing in AMMs](https://arxiv.org/abs/2403.18737)__: A new method for optimally rebalancing asset ratios in Dynamic Automated Market Maker pools could potentially increase pool profit and loss by about 25% for a BTC-ETH-DAI pool from July 2022 to June 2023. (2024-03-27, shares: 4) · https://www.ml-quant.com/papers/arxiv/2403.18737/
- __[Revisiting String Models of Interest Rates](https://arxiv.org/abs/2403.18126)__: A revised model of the forward interest rate curve, considering market forces and return correlation, accurately replicates the curve's correlation structure from 1994-2023 with less than 2% error, confirming that perceived time in interest rate markets is a sub-linear function of real time. (2024-03-26, shares: 3) · https://www.ml-quant.com/papers/arxiv/2403.18126/

## SSRN

### Quantitative

- __[Enhanced Equity Market Strategy](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781752)__: The article introduces a novel stock market strategy that enhances performance by merging a financial stress indicator with sentiment analysis. (2024-04-02, shares: 29) · https://www.ml-quant.com/papers/ssrn/4781752/
- __[Extending Financial Portfolio Methods with Deep RL](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4780026)__: The paper suggests that deep reinforcement learning can potentially improve traditional portfolio allocation strategies by incorporating contextual data and future rewards. (2024-04-01, shares: 2) · https://www.ml-quant.com/papers/ssrn/4780026/
- __[Aggregating Autoencoders for Persistent Access Threats](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781054)__: The article presents AEAPT, a deep learning method for detecting and isolating long-term, undetected cyberattacks. (2024-04-02, shares: 6) · https://www.ml-quant.com/papers/ssrn/4781054/
- __[Uncertainty in Sentiment Analysis](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4780192)__: The study explores the uncertainty in sentiment scores derived from text using advanced language processing models, finding moderate uncertainty in the results. (2024-04-01, shares: 14) · https://www.ml-quant.com/papers/ssrn/4780192/
- __[Portfolio Replication Insights](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4780148)__: The paper introduces a new method for decoding investment portfolio strategies using Dynamic Bayesian Graphical Models, resulting in better portfolio allocation decisions and adaptability to various market conditions. (2024-04-01, shares: 12) · https://www.ml-quant.com/papers/ssrn/4780148/
- __[Equity Premium Forecasting](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781195)__: Machine learning techniques, while effective in predicting equity premium within sample, struggle to beat the historical average in out-of-sample predictions. (2023-08-06, shares: 3) · https://www.ml-quant.com/papers/ssrn/4781195/
- __[China’s Inflation Rate Forecasting](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781171)__: Eight machine learning models, notably the gradient boost decision tree and forecast combination model, excel in predicting China's inflation rate over the autoregressive benchmark. (2024-03-24, shares: 4) · https://www.ml-quant.com/papers/ssrn/4781171/
- __[Predicting Beta](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4778123)__: Machine Learning algorithms enhance the precision of estimating equity betas for private or nontraded assets, particularly for smaller, younger firms with unique capital structures. (2024-01-01, shares: 2) · https://www.ml-quant.com/papers/ssrn/4778123/
- __[Deep News Sentiment for Finance](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4779994)__: The article discusses the use of neural networks to extract hidden economic factors from large news analytics data, showing superior performance in GDP growth forecasting and asset return analysis. (2023-09-12, shares: 2) · https://www.ml-quant.com/papers/ssrn/4779994/
- __[Behavioral Diversification in Portfolios](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4780990)__: The article introduces a new simulation of a diversified portfolio based on consumer products, using linear regression and Monte Carlo Simulation, advocating for a consumer-behavior approach in portfolio structuring. (2023-08-07, shares: 2) · https://www.ml-quant.com/papers/ssrn/4780990/
- __[Comparative Study of Portfolio Risk Management](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4779957)__: The article suggests a new method for portfolio risk management and capital allocation, combining value-at-risk with other statistical measures, proving its effectiveness in reducing potential portfolio losses. (2023-11-01, shares: 2) · https://www.ml-quant.com/papers/ssrn/4779957/
- __[Arbitrage Risk in MAX Effect](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4775560)__: In the Korean stock market, the MAX effect, or the highest daily return from the previous month, is only significant in overpriced stock groups. (2022-05-20, shares: 28) · https://www.ml-quant.com/papers/ssrn/4775560/

### Financial

- __[Forecasting Trading Costs](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4782032)__: The research analyzes trading costs, revealing that large, complex trades can be executed affordably and that trade risk value and complexity extend trade horizons. (2024-04-02, shares: 17) · https://www.ml-quant.com/papers/ssrn/4782032/
- __[Pricing Liquidity Risk](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4779075)__: The research investigates the pricing of liquidity factors in the US stock market, demonstrating that models with a liquidity factor outperform those with a size factor. (2024-03-30, shares: 5) · https://www.ml-quant.com/papers/ssrn/4779075/
- __[Extreme Liquidity](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4778392)__: The article proposes a crypto asset portfolio model that adjusts for liquidity to improve effectiveness and reduce discontinuity. (2024-03-30, shares: 2) · https://www.ml-quant.com/papers/ssrn/4778392/
- __[US Treasury Yield Forecast](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4780234)__: The study introduces a forecasting model for predicting the 10-Year US Treasury Yield based on variables like exchange rates and crude oil prices. (2024-04-01, shares: 7) · https://www.ml-quant.com/papers/ssrn/4780234/
- __[Intellectual Capital Growth Modeling](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4779502)__: The paper discusses a new funding mechanism that uses intellectual capital money to stimulate the generation and exploitation of intellectual capital. (2024-03-31, shares: 3) · https://www.ml-quant.com/papers/ssrn/4779502/
- __[Market Clearing](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4777585)__: The article investigates the role of firms in providing shares to passive investors, particularly in response to index funds' buying. (2024-03-29, shares: 6) · https://www.ml-quant.com/papers/ssrn/4777585/
- __[Global US Stock Integration](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781466)__: The research finds that US stocks with less global integration can improve portfolio diversification and match international index portfolios in risk-adjusted returns and tail risk. (2023-08-03, shares: 86) · https://www.ml-quant.com/papers/ssrn/4781466/
- __[Asymmetric Info in Asset Markets](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4775501)__: The study suggests that reducing information asymmetry in secondary asset markets could potentially harm economic welfare. (2022-08-19, shares: 152) · https://www.ml-quant.com/papers/ssrn/4775501/
- __[PL Attribution Options](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4775326)__: The paper disputes the belief that the gap between implied and realized volatility is the main factor in profit and loss for delta-hedged options, proposing a new formula for understanding this difference. (2023-07-07, shares: 169) · https://www.ml-quant.com/papers/ssrn/4775326/
- __[Strategic Mutual Fund Convergence](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4775467)__: The research finds a trend towards similar allocation strategies in equity mutual funds globally, especially among funds managed by large financial institutions. (2022-04-29, shares: 89) · https://www.ml-quant.com/papers/ssrn/4775467/
- __[Forecasting TSEC Volatility](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4779552)__: The study compares GARCH family models and EWMA models to identify the best algorithm for predicting volatility in Taiwan's stock market, using data from 1997 to 2023. (2023-12-31, shares: 2) · https://www.ml-quant.com/papers/ssrn/4779552/
- __[Issues with Implied Volatilities](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4780085)__: OptionMetrics records stock options prices at 359 p.m., not 400 p.m., causing changes in implied volatility spreads and affecting stock comovement, especially during the COVID-19 pandemic. (2022-03-22, shares: 2) · https://www.ml-quant.com/papers/ssrn/4780085/
- __[Improved Volatility Strategy](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4778941)__: An enhanced strategy for volatility-managed portfolios, based on Moreira and Muir 2017's formation, results in significant real-time performance improvement, including 148 Sharpe ratio increases and 165 positive abnormal returns. (2023-08-25, shares: 2) · https://www.ml-quant.com/papers/ssrn/4778941/
- __[Domain Influence on Diversification](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781579)__: A study of 251 US retail investors found diversification errors in the gain domain but not in the loss domain, supporting a loss-attention hypothesis. (2021-08-27, shares: 2) · https://www.ml-quant.com/papers/ssrn/4781579/
- __[False Discoveries in Currency Analysis](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4781905)__: A new method, robust to data dependence and estimation errors, is developed to assess predictive models' performance, when applied to currency technical trading rules, it yields a Sharpe ratio around one for about 50 years. (2024-03-06, shares: 2) · https://www.ml-quant.com/papers/ssrn/4781905/
- __[Media Sentiment and Asset Allocation](https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4778027)__: US media sentiment about foreign countries affects domestic investors' international asset allocation, with negative media coverage leading to reduced flows to international mutual funds targeting the country. (2023-05-09, shares: 2) · https://www.ml-quant.com/papers/ssrn/4778027/

## RePEc

### Finance

- __[Global Impact on Volatility Persistence](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fhdl.handle.net%2F10.1080%2F1351847X.2023.2206040%3Bh%3Drepec%3Ataf%3Aeurjfi%3Av%3A30%3Ay%3A2024%3Ai%3A5%3Ap%3A481-502)__: Global factors significantly influence the local volatility persistence in equity indices of 17 developed economies. (2024-04-03, shares: 24) · https://www.ml-quant.com/papers/repec/taf-eurjfi-v-30-y-2024-i-5-p-481-502/
- __[Insider Trading Strategies](https://econpapers.repec.org/scripts/redir.pf?u=http%3A%2F%2Fwww.scienpress.com%2FUpload%2FJAFB%252fVol%252014_2_4.pdf%3Bh%3Drepec%3Aspt%3Aapfiba%3Av%3A14%3Ay%3A2024%3Ai%3A2%3Af%3A14_2_4)__: Seyhun's 1986 study indicates that insider buying often leads to positive future returns, while insider selling slightly hints at negative returns, possibly due to liquidity needs. (2024-04-03, shares: 12) · https://www.ml-quant.com/papers/repec/spt-apfiba-v-14-y-2024-i-2-f-14-2-4/
- __[Accruals-Cash Flow Evaluation](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdoi.org%2F10.1111%2Fabac.12307%3Bh%3Drepec%3Abla%3Aabacus%3Av%3A60%3Ay%3A2024%3Ai%3A1%3Ap%3A23-48)__: This research clarifies misconceptions about the role of accruals in informative earnings, introducing a new analysis that recognizes non-cash accruals as parts of earnings that do not involve cash flows. (2024-04-03, shares: 9) · https://www.ml-quant.com/papers/repec/bla-abacus-v-60-y-2024-i-1-p-23-48/
- __[Forecasting CPI](https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fdoi.org%2F10.1002%2Ffor.3048%3Bh%3Drepec%3Awly%3Ajforec%3Av%3A43%3Ay%3A2024%3Ai%3A3%3Ap%3A702-753)__: The study enhances the precision and promptness of Consumer Price Index (CPI) forecasts by using a large Chinese news corpus and Internet search data, and combining penalized regression and mixed-frequency data sampling methods. (2024-04-03, shares: 9) · https://www.ml-quant.com/papers/repec/wly-jforec-v-43-y-2024-i-3-p-702-753/

## Machine learning

### Recently Published

- __[Rashomon Partitions: Estimating Heterogeneity](https://arxiv.org/abs/2404.02141)__: Estimating Heterogeneity: The study introduces Rashomon Partition Sets, a new method for partitioning covariate space in statistical analyses, which includes all partitions with posterior values near the maximum, allowing for more robust conclusions. (2024-04-02, shares: 8) · https://www.ml-quant.com/papers/arxiv/2404.02141/
- __[Gecko: Compact Text Embeddings](https://arxiv.org/abs/2403.20327)__: Compact Text Embeddings: Gecko is a new text embedding model that improves knowledge extraction from large language models, surpassing other models in the Massive Text Embedding Benchmark. (2024-03-29, shares: 172) · https://www.ml-quant.com/papers/arxiv/2403.20327/

### Historical Trending

- __[LightGaussian Compression](https://arxiv.org/abs/2311.17245)__: LightGaussian is a new method that converts 3D Gaussians into a more compact format, enhancing efficiency in real-time neural rendering and reducing storage needs. (2023-11-28, shares: 519) · https://www.ml-quant.com/papers/arxiv/2311.17245/
- __[Longform Factuality](http://dx.doi.org/10.48550/arxiv.2403.18802)__: The Search-Augmented Factuality Evaluator (SAFE) method uses large language models to assess the accuracy of long-form factual content, achieving superior rating performance. (2024-03-27, shares: 323) · https://www.ml-quant.com/papers/arxiv/2403.18802/
- __[FP Deep Learning Quantization](https://arxiv.org/abs/2309.14592)__: A study finds that FP8 data formats are superior to INT8 in post-training quantization, offering better workload coverage, model accuracy, and versatility across various network architectures. (2023-09-26, shares: 100) · https://www.ml-quant.com/papers/arxiv/2309.14592/
- __[Visual LVLM Grounding](https://arxiv.org/pdf/2310.05861.pdf)__: The Rephrase, Augment and Reason (RepARe) framework enhances the performance of large vision-language models in zero-shot tasks by rephrasing questions and extracting image details. (2023-10-09, shares: 127) · https://www.ml-quant.com/papers/arxiv/2310.05861/
- __[Unsupervised Diffusion Segmentation](https://arxiv.org/abs/2308.12469)__: A new method using self-attention layers in stable diffusion models achieves superior zero-shot segmentation without annotations, outperforming previous methods on the COCO-Stuff-27 dataset. (2023-08-24, shares: 107) · https://www.ml-quant.com/papers/arxiv/2308.12469/
- __[Riemannian Laplace Approximation](https://arxiv.org/abs/2311.02766)__: A recent improvement to the Laplace Approximation, which uses a Gaussian distribution to approximate a target density, corrects previous biases and narrow approximations, leading to practical improvements in experiments. (2023-11-05, shares: 75) · https://www.ml-quant.com/papers/arxiv/2311.02766/

## GitHub

### Finance

- __[Unified Time Series Forecasting Transformers](https://github.com/SalesforceAIResearch/uni2ts)__: The piece investigates a combined training approach for universal time series forecasting transformers. (2024-02-07, shares: 283)
- __[PyTorch Implementation for StockFormer](https://github.com/gsyyysg/StockFormer)__: The article showcases a PyTorch implementation of the StockFormer paper, which studies hybrid trading machines using predictive coding. (2023-07-30, shares: 62)
- __[Lightweight LLM Evaluation Suite](https://github.com/huggingface/lighteval)__: The article presents LightEval, a lightweight evaluation suite for LLM, used by Hugging Face along with the new LLM data processing library datatrove and LLM training library nanotron. (2024-01-26, shares: 267)
- __[Python Package for TradingView Screeners](https://github.com/shner-elmo/TradingView-Screener)__: The piece explores a Python package that enables users to develop TradingView screeners. (2022-05-30, shares: 112)
- __[Python Library for Nasdaq Data Links API](https://github.com/Nasdaq/data-link-python)__: The article talks about a Python library that enables access to Nasdaq Data Links' RESTful API. (2021-11-02, shares: 379)

### Trending

- __[Python QuestDB InfluxDB Client](https://github.com/questdb/py-questdb-client)__: A Python client has been created for QuestDB's InfluxDB Line Protocol. (2022-06-13, shares: 47)
- __[Rust Market Simulation Library](https://github.com/zombie-einstein/bourse)__: A Rust-based market simulation library with a Python API has been developed. (2024-02-20, shares: 13)
- __[Local and API Model Experiments](https://github.com/majacinka/crewai-experiments)__: Local and API-available models are being used in ongoing experiments. (2024-01-13, shares: 601)

## X / Twitter

### Quantitative

- __[Turing Institute Report on Language Models in Finance](https://twitter.com/carlcarrie/status/1775171956360331752)__: The report from the Alan Turning Institute explores the application of large language models in finance. (2024-04-02, shares: 0)
- __[Machine Learning for Merger Arbitrage](https://twitter.com/quantseeker/status/1773816007758401858)__: A recent study utilizes machine learning to enhance the success and potential returns of merger arbitrage trades. (2024-03-29, shares: 8)
- __[Using Option Market Data to Predict ETF Returns](https://twitter.com/quantseeker/status/1774725480412811591)__: The research paper proposes a novel trading strategy, suggesting that alterations in the implied volatility of ETF options can forecast returns on the underlying ETF. (2024-04-01, shares: 7)
- __[Weekly Recap of New Research in Finance](https://twitter.com/quantseeker/status/1775088653347270837)__: The latest weekly summary emphasizes new research in fields like asset pricing, machine learning, market microstructure, and options. (2024-04-02, shares: 6)
- __[Machine Learning and Data Science Notes](https://twitter.com/quantseeker/status/1774842986632733148)__: Ott Toomet from the University of Washington shares extensive lecture notes on machine learning and data science. (2024-04-01, shares: 5)
- __[Equity Risk Premium Update](https://twitter.com/quantseeker/status/1774374837529481261)__: Aswath Damodaran's 2024 paper update explores the elements affecting the equity risk premium and ways to calculate it. (2024-04-01, shares: 2)

### Miscellaneous

- __[ML DL, AI in Asset Management](https://twitter.com/carlcarrie/status/1775169180242673984)__: The article explores the use of Machine Learning, Deep Learning, and AI in the field of Asset Management. (2024-04-02, shares: 1)
- __[Mathematics of Neural Networks](https://twitter.com/quantseeker/status/1774110492891533690)__: Bart Smets of Eindhoven University shares lecture notes on the mathematical aspects of Neural Networks for advanced students. (2024-03-30, shares: 1)
- __[Momentum Goes Vertical](https://twitter.com/quantseeker/status/1775503088939307041)__: The article reports on a notable surge in momentum. (2024-04-03, shares: 0)
- __[Generative AI Language Model Market Map](https://twitter.com/carlcarrie/status/1775174638508654809)__: The article introduces the fast-expanding Generative AI Large Language Model Infrastructure Stack and its market landscape. (2024-04-02, shares: 0)
- __[Info for Traders](https://twitter.com/quantseeker/status/1774033557280719049)__: The article provides useful information for individuals involved in trading. (2024-03-30, shares: 0)
- __[Linear Algebra Review](https://twitter.com/quantseeker/status/1773664719724831062)__: The article provides a comprehensive review of the subject of linear algebra. (2024-03-29, shares: 0)