Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleNovember 2023
LLMs Analyzing the Analysts: Do BERT and GPT Extract More Value from Financial Analyst Reports?
- Seonmi Kim,
- Seyoung Kim,
- Yejin Kim,
- Junpyo Park,
- Seongjin Kim,
- Moolkyeol Kim,
- Chang Hwan Sung,
- Joohwan Hong,
- Yongjae Lee
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 383–391https://doi.org/10.1145/3604237.3627721This paper examines the use of Large Language Models (LLMs), specifically BERT-based models and GPT-3.5, in the sentiment analysis of Korean financial analyst reports. Due to the specialized language in these reports, traditional natural language ...
- research-articleNovember 2023
Lifting Volterra Diffusions via Kernel Decomposition
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 481–489https://doi.org/10.1145/3604237.3626914Rough volatility models have garnered considerable attention among practitioners due to their remarkable empirical fit. However, their non-Markovian nature arises from the presence of a kernel (leading to so-called Voltera diffusions), which complicates ...
- research-articleNovember 2023
Margin Trader: A Reinforcement Learning Framework for Portfolio Management with Margin and Constraints
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 610–618https://doi.org/10.1145/3604237.3626906In the field of portfolio management using reinforcement learning, existing approaches have mainly focused on cash-only trading, overlooking the potential benefits and risks of margin trading. Incorporating margin accounts and their constraints, ...
- research-articleNovember 2023
From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 82–90https://doi.org/10.1145/3604237.3626905Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often ...
- research-articleNovember 2023
Dynamic Time Warping for Lead-Lag Relationship Detection in Lagged Multi-Factor Models
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 454–462https://doi.org/10.1145/3604237.3626904In multivariate time series systems, lead-lag relationships reveal dependencies between time series when they are shifted in time relative to each other. Uncovering such relationships is valuable in downstream tasks, such as control, forecasting, and ...
-
- research-articleNovember 2023
Graph Denoising Networks: A Deep Learning Framework for Equity Portfolio Construction
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 193–201https://doi.org/10.1145/3604237.3626903Graph-based deep learning is a rapidly evolving and practical field due to the ubiquity of graph data and its flexible topology. Although many graph learning frameworks show impressive capabilities, their outputs begin to deteriorate for sufficiently ...
- research-articleNovember 2023
Turbo-Charging Deep Learning Methods for Partial Differential Equations
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 150–158https://doi.org/10.1145/3604237.3626900Solving partial differential equations (PDEs) is a frequent necessity in numerous domains, ranging from complex systems simulation to financial derivatives pricing and continuous-time optimisation tasks. The challenging nature of PDEs, especially in ...
- research-articleNovember 2023
A Fast Non-Linear Coupled Tensor Completion Algorithm for Financial Data Integration and Imputation
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 409–417https://doi.org/10.1145/3604237.3626899Missing data imputation is crucial in finance to ensure accurate financial analysis, risk management, investment strategies, and other financial applications. Recently, tensor factorization and completion have gained momentum in many finance data ...
- research-articleNovember 2023
Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 91–99https://doi.org/10.1145/3604237.3626898Developing a generative model of realistic order flow in financial markets is a challenging open problem, with numerous applications for market participants. Addressing this, we propose the first end-to-end autoregressive generative model that generates ...
- research-articleNovember 2023
Bayesian Networks Improve Out-of-Distribution Calibration for Agribusiness Delinquency Risk Assessment
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 244–252https://doi.org/10.1145/3604237.3626897Automated credit risk assessment plays an important role in agricultural lending. However, credit risk assessment in the agricultural domain has unique challenges due to the impact of weather, pest outbreaks, commodities market dynamics, and other ...
- research-articleNovember 2023
NFT Primary Sale Price and Secondary Sale Prediction via Deep Learning
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 116–123https://doi.org/10.1145/3604237.3626896Non Fungible Tokens (NFTs) are blockchain-based unique digital assets defining ownership deeds. They can characterize various different objects such as collectible, art, and in-game items. In general, NFTs are encoded by blockchains smart contracts, and ...
- research-articleNovember 2023
On Correlated Stock Market Time Series Generation
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 524–532https://doi.org/10.1145/3604237.3626895In this paper, we present CoMeTS-GAN (Correlated Multivariate Time Series GAN), a framework based on Conditional Generative Adversarial Networks (C-GANs), designed to generate mid-prices and volumes time series of correlated stocks. This tool provides a ...
- research-articleNovember 2023
A GANs-Based Approach for Stock Price Anomaly Detection and Investment Risk Management
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 1–9https://doi.org/10.1145/3604237.3626892This paper addresses the challenges of risk management in the financial market through a data-driven approach. In investment management, it is important to detect and avoid market anomalies, defined as significant deviations from typical stock price ...
- research-articleNovember 2023
Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 392–400https://doi.org/10.1145/3604237.3626891Standard Full-Data classifiers in NLP demand thousands of labeled examples, which is impractical in data-limited domains. Few-shot methods offer an alternative, utilizing contrastive learning techniques that can be effective with as little as 20 examples ...
- research-articleNovember 2023
Improving the Robustness of Financial Models through Identification of the Minimal Vulnerable Feature Set
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 297–304https://doi.org/10.1145/3604237.3626890Research in adversarial robustness has primarily focused on neural networks in domains like computer vision, neglecting heterogeneous tabular datasets prevalent in finance. The financial domain, in particular, faces a heightened risk, where malicious ...
- research-articleNovember 2023
Reinforcement Learning for Combining Search Methods in the Calibration of Economic ABMs
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 305–313https://doi.org/10.1145/3604237.3626889Calibrating agent-based models (ABMs) in economics and finance typically involves a derivative-free search in a very large parameter space. In this work, we benchmark a number of search methods in the calibration of a well-known macroeconomic ABM on ...
- research-articleNovember 2023
Modeling Inverse Demand Function with Explainable Dual Neural Networks
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 108–115https://doi.org/10.1145/3604237.3626887Financial contagion has been widely recognized as a fundamental risk to the financial system. Particularly potent is price-mediated contagion, wherein forced liquidations by firms depress asset prices and propagate financial stress, enabling crises to ...
- research-articleNovember 2023
DRL Trading with CPT Actor and Truncated Quantile Critics
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 574–582https://doi.org/10.1145/3604237.3626886The Cumulative Prospect Theory (CPT) is a popular behavioral decision-making model that has been shown to reflect humans’ risk-sensitive behavior. This work develops an end-to-end CPT-based DRL trading agent. For our architecture, we draw on the ...
- research-articleNovember 2023
Generative Machine Learning for Multivariate Equity Returns
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 159–166https://doi.org/10.1145/3604237.3626884The use of machine learning to generate synthetic data has grown in popularity with the proliferation of text-to-image models and especially large language models. The core methodology these models use is to learn the distribution of the underlying data, ...
- research-articleNovember 2023
The GANfather: Controllable generation of malicious activity to improve defence systems
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in FinancePages 133–140https://doi.org/10.1145/3604237.3626882Machine learning methods to aid defence systems in detecting malicious activity typically rely on labelled data. In some domains, such labelled data is unavailable or incomplete. In practice this can lead to low detection rates and high false positive ...