[1] From Factor Models to Deep Learning从因子模型到深度学习来源:ARXIV_20240312[2] Generative Probabilistic Forecasting with Applications in Market Operations生成概率预测及其在市场运作中的应用来源:ARXIV_20240312[3] Study of the Impact of the Big Data Era on Accounting and Auditing大数据时代对会计审计的影响研究来源:ARXIV_20240313[4] Machine Learning Approach for Predicting U.S. ETFs’ Tracking Errors – Implications on U.S. Invested Fund预测美国ETF跟踪误差的机器学习方法——对美国投资基金的启示来源:SSRN_20240313[5] Return Predictability: Accounting versus Market Information收益可预测性：会计与市场信息来源:SSRN_20240313[6] Measuring Information Quality by Topic Attention Divergence: Evidence from Earnings Calls通过话题注意力差异衡量信息质量——来自财报电话会议的证据来源:SSRN_20240313[7] Market Model Calibration via Neural Network基于神经网络的市场模型校准来源:SSRN_20240313
[1] From Factor Models to Deep Learning
标题:从因子模型到深度学习作者:Junyi Ye, Bhaskar Goswami, Jingyi Gu, Ajim Uddin, Guiling Wang来源:ARXIV_20240312Abstract : This paper comprehensively reviews the application of machine learning (ML) and AI in finance, specifically in the context of asset pricing. It starts by summarizing the traditional asset pricing models and examining their limitations in capturing the complexities of financial markets. It explores how 1) ML models, including supervised, unsupervised, semi supervised, and reinforcement learning, provide versatile frameworks to address these......(摘要翻译及全文见知识星球)Keywords :
[2] Generative Probabilistic Forecasting with Applications in Market Operations
标题:生成概率预测及其在市场运作中的应用作者:Xinyi Wang, Lang Tong来源:ARXIV_20240312Abstract : This paper presents a novel generative probabilistic forecasting approach derived from the Wiener Kallianpur innovation representation of nonparametric time series. Under the paradigm of generative artificial intelligence, the proposed forecasting architecture includes an autoencoder that transforms nonparametric multivariate random processes into canonical innovation sequences, from which future time series samples are generated according to their probability distributions conditioned on past samples.......(摘要翻译及全文见知识星球)Keywords :
[3] Study of the Impact of the Big Data Era on Accounting and Auditing
标题:大数据时代对会计审计的影响研究作者:Yuxiang Sun, Jingyi Li, Mengdie Lu, Zongying Guo来源:ARXIV_20240313
Abstract : Big data revolutionizes accounting and auditing, offering deep insights but also introducing challenges like data privacy and security. With data from IoT, social media, and transactions, traditional practices are evolving. Professionals must adapt to these changes, utilizing AI and machine learning for efficient data analysis and anomaly detection. Key to overcoming these challenges are enhanced analytics tools, continuous learning, and industry......(摘要翻译及全文见知识星球)Keywords :
[4] Machine Learning Approach for Predicting U.S. ETFs’ Tracking Errors – Implications on U.S. Invested Fund
标题:预测美国ETF跟踪误差的机器学习方法——对美国投资基金的启示作者:Jinhyung (Eric) Cho,Gun Hee Lee,Woneung Lee,Bongjun Kim来源:SSRN_20240313Abstract : In recent decades, machine learning (ML) algorithms has gained wide popularity in the finance literature. The goal of this research is to exploit machine learning techniques in order to analyze the effect of exchange-traded fund (ETF) illiquidity on tracking errors. We demonstrate the superior performance of the machine learning models – Random Forest and Gradient Boosting Decision Tree, in particular -......(摘要翻译及全文见知识星球)Keywords : ETF, Tracking Error, Machine Learning, SHAP
[5] Return Predictability: Accounting versus Market Information
标题:收益可预测性：会计与市场信息作者:Paul Geertsema,Helen Lu来源:SSRN_20240313Abstract : Existing research emphasizes the dominance of market-based predictors, such as price trends and liquidity measures, in the context of stock return prediction. However, we find that accounting-based predictors consistently outperform market-based predictors at forecast horizons beyond one month. This performance gap is robust to size and liquidity, and more pronounced in the recent sample period. Our analysis suggests that the dominance......(摘要翻译及全文见知识星球)Keywords : Long-run returns, return predictability, cross-section of returns, machine learning, value-relevance, variable importance, SHAP values
[6] Measuring Information Quality by Topic Attention Divergence: Evidence from Earnings Calls
标题:通过话题注意力差异衡量信息质量——来自财报电话会议的证据作者:Zicheng Xiao来源:SSRN_20240313Abstract : Leveraging computational linguistics and 20 million turns of dialogues from earnings conference calls over the period 2006-2022, I introduce a novel measure that quantifies the disparity in narrative focus between managers’ disclosures and analysts’ questions during these calls, denoted as Topic Attention Divergence(TAD). A higher level of TAD indicates a higher level of firm-investor asymmetry and lower information quality. My results......(摘要翻译及全文见知识星球)Keywords : Information Quality, Voluntary Disclosure, Conference Call, Topic Classification, Cost of Capital, FinTech, NLP, Large Language Model
[7] Market Model Calibration via Neural Network
标题:基于神经网络的市场模型校准作者:Davide Gianatti,Gianluca Molteni,Serena Manti来源:SSRN_20240313Abstract : Many market models require substantial computational time to be calibrated, posing a significant barrier to some practical applications. We propose a solution to the problem exploiting machine learning methods: the calibration procedure is approximated by a fast neural network. Following the observation that having a good data set is crucial to train an efficient neural network, we have put our focus......(摘要翻译及全文见知识星球)Keywords : Neural Network, Model Calibration, Computational Time, Interest Rates, HJM model, HJM-FMM model, Training Set Generation, Stochastic Dynamics
