Proceedings of the First ACM International Conference on AI in Finance最新文献_第5页

Quantifying ESG alpha using scholar big data: an automated machine learning approach 使用学者大数据量化ESG alpha:一种自动化机器学习方法

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-05-30 DOI: 10.1145/3383455.3422529

Qian Chen, Xiao-Yang Liu

{"title":"Quantifying ESG alpha using scholar big data: an automated machine learning approach","authors":"Qian Chen, Xiao-Yang Liu","doi":"10.1145/3383455.3422529","DOIUrl":"https://doi.org/10.1145/3383455.3422529","url":null,"abstract":"ESG (Environmental, social and governance) alpha strategy that makes sustainable investment has gained popularity among investors. The ESG fields of study in scholar big data is a valuable alternative data that reflects a company's long-term ESG commitment. However, it is considered a difficulty to quantitatively measure a company's ESG premium and its impact to the company's stock price using scholar big data. In this paper, we utilize ESG scholar data as alternative data to develop an automatic trading strategy and propose a practical machine learning approach to quantify the ESG premium of a company and capture the ESG alpha. First, we construct our ESG investment universe and apply feature engineering on the companies' ESG scholar data from the Microsoft Academic Graph database. Then, we train six complementary machine learning models using a combination of financial indicators and ESG scholar data features and employ an ensemble method to predict stock prices and automatically set up portfolio allocation. Finally, we manage our portfolio, trade and rebalance the portfolio allocation monthly using predicted stock prices. We backtest our ESG alpha strategy and compare its performance with benchmarks. The proposed ESG alpha strategy achieves a cumulative return of 2,154.4% during the backtesting period of ten years, which significantly outperforms the NASDAQ-100 index's 397.4% and S&P 500's 226.9%. The traditional financial indicators results in only 1,443.7%, thus our scholar data-based ESG alpha strategy is better at capturing ESG premium than traditional financial indicators.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114688342","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Sig-SDEs model for quantitative finance 量化金融的Sig-SDEs模型

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-05-30 DOI: 10.1145/3383455.3422553

Imanol Perez Arribas, C. Salvi, L. Szpruch

引用次数: 38

Option hedging with risk averse reinforcement learning 基于风险厌恶强化学习的期权对冲

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-05-29 DOI: 10.1145/3383455.3422532

Edoardo Vittori, M. Trapletti, Marcello Restelli

引用次数: 13

Machine learning fund categorizations 机器学习基金分类

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-05-29 DOI: 10.1145/3383455.3422555

D. Mehta, Dhruv Desai, Jithin Pradeep

引用次数: 5

Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity 在标签稀缺的情况下，机器学习方法检测比特币区块链中的洗钱行为

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-05-29 DOI: 10.1145/3383455.3422549

Joana Lorenz, Maria Inês Silva, David Oliveira Aparício, João Tiago Ascensão, P. Bizarro

引用次数: 59

Conditional mutual information-based contrastive loss for financial time series forecasting 基于条件互信息的金融时间序列对比损失预测

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-02-18 DOI: 10.1145/3383455.3422550

Hanwei Wu, Ather Gattami, M. Flierl

{"title":"Conditional mutual information-based contrastive loss for financial time series forecasting","authors":"Hanwei Wu, Ather Gattami, M. Flierl","doi":"10.1145/3383455.3422550","DOIUrl":"https://doi.org/10.1145/3383455.3422550","url":null,"abstract":"We present a representation learning framework for financial time series forecasting. One challenge of using deep learning models for finance forecasting is the shortage of available training data when using small datasets. Direct trend classification using deep neural networks trained on small datasets is susceptible to the overfitting problem. In this paper, we propose to first learn compact representations from time series data, then use the learned representations to train a simpler model for predicting time series movements. We consider a class-conditioned latent variable model. We train an encoder network to maximize the mutual information between the latent variables and the trend information conditioned on the encoded observed variables. We show that conditional mutual information maximization can be approximated by a contrastive loss. Then, the problem is transformed into a classification task of determining whether two encoded representations are sampled from the same class or not. This is equivalent to performing pairwise comparisons of the training datapoints, and thus, improves the generalization ability of the encoder network. We use deep autoregressive models as our encoder to capture long-term dependencies of the sequence data. Empirical experiments indicate that our proposed method has the potential to advance state-of-the-art performance.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"8 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114135328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

Optimal, truthful, and private securities lending 最优的、真实的、私人的证券借贷

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2019-12-12 DOI: 10.1145/3383455.3422541

Emily Diana, Michael Kearns, S. Neel, Aaron Roth

{"title":"Optimal, truthful, and private securities lending","authors":"Emily Diana, Michael Kearns, S. Neel, Aaron Roth","doi":"10.1145/3383455.3422541","DOIUrl":"https://doi.org/10.1145/3383455.3422541","url":null,"abstract":"We consider a fundamental dynamic allocation problem motivated by the problem of securities lending in financial markets, the mechanism underlying the short selling of stocks. A lender would like to distribute a finite number of identical copies of some scarce resource to n clients, each of whom has a private demand that is unknown to the lender. The lender would like to maximize the usage of the resource --- avoiding allocating more to a client than her true demand --- but is constrained to sell the resource at a pre-specified price per unit, and thus cannot use prices to incentivize truthful reporting. We first show that the Bayesian optimal algorithm for the one-shot problem --- which maximizes the resource's expected usage according to the posterior expectation of demand, given reports --- actually incentivizes truthful reporting as a dominant strategy. Because true demands in the securities lending problem are often sensitive information that the client would like to hide from competitors, we then consider the problem under the additional desideratum of (joint) differential privacy. We give an algorithm, based on simple dynamics for computing market equilibria, that is simultaneously private, approximately optimal, and approximately dominant-strategy truthful. Finally, we leverage this private algorithm to construct an approximately truthful, optimal mechanism for the extensive form multi-round auction where the lender does not have access to the true joint distributions between clients' requests and demands.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130110006","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Get real: realism metrics for robust limit order book market simulations 现实:现实主义指标稳健的限价订单市场模拟

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2019-12-10 DOI: 10.1145/3383455.3422561

Svitlana Vyetrenko, David Byrd, Nick Petosa, Mahmoud Mahfouz, Danial Dervovic, M. Veloso, T. Balch

{"title":"Get real: realism metrics for robust limit order book market simulations","authors":"Svitlana Vyetrenko, David Byrd, Nick Petosa, Mahmoud Mahfouz, Danial Dervovic, M. Veloso, T. Balch","doi":"10.1145/3383455.3422561","DOIUrl":"https://doi.org/10.1145/3383455.3422561","url":null,"abstract":"Market simulation is an increasingly important method for evaluating and training trading strategies and testing \"what if\" scenarios. The extent to which results from these simulations can be trusted depends on how realistic the environment is for the strategies being tested. As a step towards providing benchmarks for realistic simulated markets, we enumerate measurable stylized facts of limit order book (LOB) markets across multiple asset classes from the literature. We apply these metrics to data from real markets and compare the results to data originating from simulated markets. We illustrate their use in five different simulated market configurations: The first (market replay) is frequently used in practice to evaluate trading strategies; the other four are interactive agent based simulation (IABS) configurations which combine zero intelligence agents, and agents with limited strategic behavior. These simulated agents rely on an internal \"oracle\" that provides a fundamental value for the asset. In traditional IABS methods the fundamental originates from a mean reverting random walk. We show that markets exhibit more realistic behavior when the fundamental arises from historical market data. We further experimentally illustrate the effectiveness of IABS techniques as opposed to market replay.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121920089","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 46

Explainable clustering and application to wealth management compliance 可解释的聚类及其在财富管理合规中的应用

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2019-09-29 DOI: 10.1145/3383455.3422530

Enguerrand Horel, K. Giesecke, Victor Storchan, Naren Chittar

引用次数: 8

Trading via image classification 通过图像分类进行交易

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2019-07-23 DOI: 10.1145/3383455.3422544

N. Cohen, T. Balch, M. Veloso

{"title":"Trading via image classification","authors":"N. Cohen, T. Balch, M. Veloso","doi":"10.1145/3383455.3422544","DOIUrl":"https://doi.org/10.1145/3383455.3422544","url":null,"abstract":"The art of systematic financial trading evolved with an array of approaches, ranging from simple strategies to complex algorithms, all relying primarily on aspects of time-series analysis (e.g., Murphy, 1999; De Prado, 2018; Tsay, 2005). After visiting the trading floor of a leading financial institution, we noticed that traders always execute their trade orders while observing images of financial time-series on their screens. In this work, we build upon image recognition's success (e.g., Krizhevsky et al., 2012; Szegedy et al., 2015; Zeiler and Fergus, 2014; Wang et al., 2017; Koch et al., 2015; LeCun et al., 2015) and examine the value of transforming the traditional time-series analysis to that of image classification. We create a large sample of financial time-series images encoded as candlestick (Box and Whisker) charts and label the samples following three algebraically-defined binary trade strategies (Murphy, 1999). Using the images, we train over a dozen machine-learning classification models and find that the algorithms efficiently recover the complicated, multiscale label-generating rules when the data is visually represented. We suggest that the transformation of continuous numeric time-series classification problem to a vision problem is useful for recovering signals typical of technical analysis.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"292 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134601928","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 25