Real-world financial documents report essential information about an entity's financial holdings that can span millions of different financial instrument types. Yet, these details are often buried in messy, multi-page, fragmented tables - for example, 99.4% of the tables in our dataset have no bounding boxes with the maximum number of rows amounting to 426 per table across 44 pages. To tackle these unique challenges from real-world tables, we present a continuously learning, agentic table extraction system, TASER (Table Agents for Schema-guided Extraction and Recommendation) that extracts highly unstructured, multi-page, heterogeneous tables into normalized, schema-conforming outputs. Our table agents execute on table detection, classification, extraction, and recommendations by leveraging an initial schema. Then, our Recommender Agent reviews the outputs, recommends schema revisions, and decides on the final recommendations, enabling TASER to outperform existing table detection models such as Table Transformer by 10.1%. Within this continuous learning process, we highlight that larger batch sizes result in a 104.3% increase in schema recommendations that are actionable and utilized, resulting in a 9.8% increase in extracted holdings - highlighting the importance of a continuous learning process. To train TASER, we have manually labeled 22,584 pages (28,150,449 tokens), 3,213 tables for $731,685,511,687 of holdings culminating in one of the first real financial table datasets. We release our dataset TASERTab to enable the research community to access real-world financial tables and outputs. Our results highlight the promise of agentic, schema-guided extraction systems for robust understanding of real-world financial tables.

This paper presents a comprehensive study on the use of ensemble Reinforcement Learning (RL) models in financial trading strategies, leveraging classifier models to enhance performance. By combining RL algorithms such as A2C, PPO, and SAC with traditional classifiers like Support Vector Machines (SVM), Decision Trees, and Logistic Regression, we investigate how different classifier groups can be integrated to improve risk-return trade-offs. The study evaluates the effectiveness of various ensemble methods, comparing them with individual RL models across key financial metrics, including Cumulative Returns, Sharpe Ratios (SR), Calmar Ratios, and Maximum Drawdown (MDD). Our results demonstrate that ensemble methods consistently outperform base models in terms of risk-adjusted returns, providing better management of drawdowns and overall stability. However, we identify the sensitivity of ensemble performance to the choice of variance threshold {\tau}, highlighting the importance of dynamic {\tau} adjustment to achieve optimal performance. This study emphasizes the value of combining RL with classifiers for adaptive decision-making, with implications for financial trading, robotics, and other dynamic environments.

Recent deep reinforcement learning (DRL) methods in finance show promising outcomes. However, there is limited research examining the behavior of these DRL algorithms. This paper aims to investigate their tendencies towards holding or trading financial assets as well as purchase diversity. By analyzing their trading behaviors, we provide insights into the decision-making processes of DRL models in finance applications. Our findings reveal that each DRL algorithm exhibits unique trading patterns and strategies, with A2C emerging as the top performer in terms of cumulative rewards. While PPO and SAC engage in significant trades with a limited number of stocks, DDPG and TD3 adopt a more balanced approach. Furthermore, SAC and PPO tend to hold positions for shorter durations, whereas DDPG, A2C, and TD3 display a propensity to remain stationary for extended periods.

We consider the design of strategies for market making in an exchange. A market maker generally seeks to profit from the difference between the buy and sell price of an asset, yet the market maker also takes exposure risk in the event of large price movements. Profit guarantees for market making strategies have typically required certain stochastic assumptions on the price fluctuations of the asset in question; for example, assuming a model in which the price process is mean reverting. We propose a class of "spread-based" market making strategies whose performance can be controlled even under worst-case (adversarial) settings. We prove structural properties of these strategies which allows us to design a master algorithm which obtains low regret relative to the best such strategy in hindsight. We run a set of experiments showing favorable performance on recent real-world stock price data.

Crowding is widely regarded as one of the most important risk factors in designing portfolio strategies. In this paper, we analyze stock crowding using network analysis of fund holdings, which is used to compute crowding scores for stocks. These scores are used to construct costless long-short portfolios, computed in a distribution-free (model-free) way and without using any numerical optimization, with desirable properties of hedge portfolios. More speciTically, these long-short portfolios provide protection for both small and large market price Tluctuations, due to their negative correlation with the market and positive convexity as a function of market returns. By adding our long-short portfolio to a baseline portfolio such as a traditional 60/40 portfolio, our method provides an alternative way to hedge portfolio risk including tail risk, which does not require costly option-based strategies or complex numerical optimization.

BigBear.ai Holdings, Inc. (NYSE:BBAI) is soaring in the past few weeks as retail investors return to the market. What companies are well-positioned to participate in this nascent and rapidly growing market opportunity? On the surface, BigBear.ai has the right narrative. BigBear.ai is focusing on empowering customers to make the right decisions, at the right time, every time. However, spending a few moments beyond its catchy slogan and the investment case rapidly falls apart.

It's not often we see technologies gain exponential adoption and attention in a very short time frame the same way OpenAI's ChatGPT has since late 2022. ChatGPT is estimated to have reached 100 million users in just two months.1 It took Netflix 10 years to reach 100 million users; six and half years for Google Translate; roughly two and a half years for Instagram; and about nine months for TikTok.2,3 Generative artificial intelligence (AI) is a rapidly evolving field that has the potential to revolutionize many industries. This powerful technology uses deep learning algorithms to create new and original content, ranging from text and images to music and 3D models.

In late January, the world of artificial intelligence went mainstream when popular online media company BuzzFeed announced it was planning to use artificial intelligence software called API to help it generate content. OpenAI, the company that created API, also made the more popular ChatGPT, released in November of 2022. API and ChatGPT have been used to write emails and create quizzes and listicles. It has even been used to write reports on popular books and other essay-style assignments for high school and college students. While we have all heard about the potential of artificial intelligence for years, BuzzFeed taking the plunge and using it to create content is a big deal.

SoftBank-backed Z Holdings will merge its two wholly owned subsidiaries -- Yahoo Japan and messaging app Line -- by March 2024 to streamline its operations in a bid to position itself as a world-leading artificial intelligence company. Z Holdings President Kentaro Kawabe made the announcement Thursday after the decision was approved by its board of directors, but details are yet to be made public. Line President and Z Holdings co-CEO Takeshi Idezawa will become Z Holdings president on April 1, while Kawabe will become chairman. This could be due to a conflict with your ad-blocking or security software. Please add japantimes.co.jp and piano.io to your list of allowed sites.

WNS (Holdings) Limited (NYSE: WNS), is a leading Business Process Management (BPM) company. We combine our deep industry knowledge with technology and analytics expertise to co-create innovative, digital-led transformational solutions with clients across 10 industries. We enable businesses in Travel, Insurance, Banking and Financial Services, Manufacturing, Retail and Consumer Packaged Goods, Shipping and Logistics, Healthcare, and Utilities to re-imagine their digital future and transform their outcomes with operational excellence. We deliver an entire spectrum of BPM services in finance and accounting, procurement, customer interaction services and human resources leveraging collaborative models that are tailored to address the unique business challenges of each client. We co-create and execute the future vision of 400 clients with the help of our 44,000 employees.