Proceedings of the First ACM International Conference on AI in Finance最新文献_第4页

SURF: improving classifiers in production by learning from busy and noisy end users SURF:通过向繁忙和嘈杂的最终用户学习来改进生产中的分类器

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-10-12 DOI: 10.1145/3383455.3422547

J. Lockhart, Samuel A. Assefa, Ayham Alajdad, Andrew Alexander, T. Balch, M. Veloso

引用次数: 563

CryptoCredit: securely training fair models CryptoCredit:安全地训练公平模型

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-10-09 DOI: 10.1145/3383455.3422567

Leo de Castro, Jiahao Chen, Antigoni Polychroniadou

引用次数: 2

Towards self-regulating AI: challenges and opportunities of AI model governance in financial services 走向自我调节的人工智能:金融服务中人工智能模型治理的挑战与机遇

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-10-09 DOI: 10.1145/3383455.3422564

Eren Kurshan, Hongda Shen, Jiahao Chen

{"title":"Towards self-regulating AI: challenges and opportunities of AI model governance in financial services","authors":"Eren Kurshan, Hongda Shen, Jiahao Chen","doi":"10.1145/3383455.3422564","DOIUrl":"https://doi.org/10.1145/3383455.3422564","url":null,"abstract":"AI systems have found a wide range of application areas in financial services. Their involvement in broader and increasingly critical decisions has escalated the need for compliance and effective model governance. Current governance practices have evolved from more traditional financial applications and modeling frameworks. They often struggle with the fundamental differences in AI characteristics such as uncertainty in the assumptions, and the lack of explicit programming. AI model governance frequently involves complex review flows and relies heavily on manual steps. As a result, it faces serious challenges in effectiveness, cost, complexity, and speed. Furthermore, the unprecedented rate of growth in the AI model complexity raises questions on the sustainability of the current practices. This paper focuses on the challenges of AI model governance in the financial services industry. As a part of the outlook, we present a system-level framework towards increased self-regulation for robustness and compliance. This approach aims to enable potential solution opportunities through increased automation and the integration of monitoring, management, and mitigation capabilities. The proposed framework also provides model governance and risk management improved capabilities to manage model risk during deployment.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114524567","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: 20

Paying down metadata debt: learning the representation of concepts using topic models 偿还元数据债务:使用主题模型学习概念的表示

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-10-09 DOI: 10.1145/3383455.3422537

Jiahao Chen, M. Veloso

引用次数: 1

Choosing news topics to explain stock market returns 选择新闻话题来解释股市回报

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-10-06 DOI: 10.1145/3383455.3422557

P. Glasserman, K. Krstovski, Paul Laliberte, Harry Mamaysky

引用次数: 12

Deep reinforcement learning for automated stock trading: an ensemble strategy 用于自动股票交易的深度强化学习:一个集成策略

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-09-11 DOI: 10.1145/3383455.3422540

Hongyang Yang, Xiao-Yang Liu, Shanli Zhong, A. Walid

{"title":"Deep reinforcement learning for automated stock trading: an ensemble strategy","authors":"Hongyang Yang, Xiao-Yang Liu, Shanli Zhong, A. Walid","doi":"10.1145/3383455.3422540","DOIUrl":"https://doi.org/10.1145/3383455.3422540","url":null,"abstract":"Stock trading strategies play a critical role in investment. However, it is challenging to design a profitable strategy in a complex and dynamic stock market. In this paper, we propose an ensemble strategy that employs deep reinforcement schemes to learn a stock trading strategy by maximizing investment return. We train a deep reinforcement learning agent and obtain an ensemble trading strategy using three actor-critic based algorithms: Proximal Policy Optimization (PPO), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG). The ensemble strategy inherits and integrates the best features of the three algorithms, thereby robustly adjusting to different market situations. In order to avoid the large memory consumption in training networks with continuous action space, we employ a load-on-demand technique for processing very large data. We test our algorithms on the 30 Dow Jones stocks that have adequate liquidity. The performance of the trading agent with different reinforcement learning algorithms is evaluated and compared with both the Dow Jones Industrial Average index and the traditional min-variance portfolio allocation strategy. The proposed deep ensemble strategy is shown to outperform the three individual algorithms and two baselines in terms of the risk-adjusted return measured by the Sharpe ratio.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131916028","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: 127

Navigating the dynamics of financial embeddings over time 驾驭金融嵌入的动态

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-07-01 DOI: 10.1145/3383455.3422552

Antonia Gogoglou, Brian Nguyen, A. Salimov, Jonathan Rider, C. B. Bruss

引用次数: 5

Risk-sensitive reinforcement learning: a martingale approach to reward uncertainty 风险敏感强化学习:奖励不确定性的鞅方法

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-06-23 DOI: 10.1145/3383455.3422519

N. Vadori, Sumitra Ganesh, P. Reddy, M. Veloso

引用次数: 6

Generating synthetic data in finance: opportunities, challenges and pitfalls 金融合成数据的生成:机遇、挑战和陷阱

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-06-23 DOI: 10.1145/3383455.3422554

Samuel A. Assefa

{"title":"Generating synthetic data in finance: opportunities, challenges and pitfalls","authors":"Samuel A. Assefa","doi":"10.1145/3383455.3422554","DOIUrl":"https://doi.org/10.1145/3383455.3422554","url":null,"abstract":"Financial services generate a huge volume of data that is extremely complex and varied. These datasets are often stored in silos within organisations for various reasons, including but not limited to regulatory requirements and business needs. As a result, data sharing within different lines of business as well as outside of the organisation (e.g. to the research community) is severely limited. It is therefore critical to investigate methods for synthesising financial datasets that follow the same properties of the real data while respecting the need for privacy of the parties involved. This introductory paper aims to highlight the growing need for effective synthetic data generation in the financial domain. We highlight three main areas of focus that are of particular importance while generating synthetic financial datasets: 1) Generating realistic synthetic datasets. 2) Measuring the similarities between real and generated datasets. 3) Ensuring the generative process satisfies any privacy constraints. Although these challenges are also present in other domains, the additional regulatory and privacy requirements within financial services present unique questions that are not asked elsewhere. Due to the size and influence of the financial services industry, answering these questions has the potential for a great and lasting impact. Finally, we aim to develop a shared vocabulary and context for generating synthetic financial data using two types of financial datasets as examples.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121473776","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: 96

Multi-agent reinforcement learning in a realistic limit order book market simulation 多智能体强化学习在现实限价订单市场模拟中的应用

Proceedings of the First ACM International Conference on AI in Finance Pub Date : 2020-06-10 DOI: 10.1145/3383455.3422570

Michael Karpe, Jin Fang, Zhongyao Ma, Chen Wang

{"title":"Multi-agent reinforcement learning in a realistic limit order book market simulation","authors":"Michael Karpe, Jin Fang, Zhongyao Ma, Chen Wang","doi":"10.1145/3383455.3422570","DOIUrl":"https://doi.org/10.1145/3383455.3422570","url":null,"abstract":"Optimal order execution is widely studied by industry practitioners and academic researchers because it determines the profitability of investment decisions and high-level trading strategies, particularly those involving large volumes of orders. However, complex and unknown market dynamics pose significant challenges for the development and validation of optimal execution strategies. In this paper, we propose a model-free approach by training Reinforcement Learning (RL) agents in a realistic market simulation environment with multiple agents. First, we configure a multi-agent historical order book simulation environment for execution tasks built on an Agent-Based Interactive Discrete Event Simulation (ABIDES) [6]. Second, we formulate the problem of optimal execution in an RL setting where an intelligent agent can make order execution and placement decisions based on market microstructure trading signals in High Frequency Trading (HFT). Third, we develop and train an RL execution agent using the Double Deep Q-Learning (DDQL) algorithm in the ABIDES environment. In some scenarios, our RL agent converges towards a Time-Weighted Average Price (TWAP) strategy. Finally, we evaluate the simulation with our RL agent by comparing it with a market replay simulation using real market Limit Order Book (LOB) data.","PeriodicalId":447950,"journal":{"name":"Proceedings of the First ACM International Conference on AI in Finance","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127616651","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: 27