Financial Machine Learning Research Articles

Reinforcement prompting for financial synthetic data generation

The emergence of Large Language Models (LLMs) has unlocked unprecedented potential for comprehending and generating human-like text, fueling advances in the finance domain – a tool that can shape investment strategies and market predictions. Nevertheless, challenges stemming from the necessity for extensive labeled data and the imperative for data privacy remain. The generation of high-quality synthetic data emerges as a promising avenue to circumvent these issues. In this paper, we introduce a novel methodology, named “Reinforcement Prompting”, to address these challenges. Our strategy employs a policy network as a Selector to generate prompts, and an LLM as an Executor to produce financial synthetic data. This synthetic data generation process preserves data privacy and mitigates the dependency on real-world labeled datasets. We validate the effectiveness of our approach through experimental evaluations. Our results indicate that models trained on synthetic data generated via our approach exhibit competitive performance when compared to those trained on actual financial data, thereby bridging the performance gap. This research provides a novel solution to the challenges of data privacy and labeled data scarcity in financial sentiment analysis, offering considerable advancement in the field of financial machine learning.

Portfolio construction using explainable reinforcement learning

AbstractWhile machine learning's role in financial trading has advanced considerably, algorithmic transparency and explainability challenges still exist. This research enriches prior studies focused on high‐frequency financial data prediction by introducing an explainable reinforcement learning model for portfolio management. This model transcends basic asset prediction, formulating concrete, actionable trading strategies. The methodology is applied in a custom trading environment mimicking the CAC‐40 index's financial conditions, allowing the model to adapt dynamically to market changes based on iterative learning from historical data. Empirical findings reveal that the model outperforms an equally weighted portfolio in out‐of‐sample tests. The study offers a dual contribution: it elevates algorithmic planning while significantly boosting transparency and interpretability in financial machine learning. This approach tackles the enduring ‘black‐box’ issue and provides a holistic, transparent framework for managing investment portfolios.

Predicting Cryptocurrency Returns Using Classification and Regression Machine Learning Model

People are starting to see the cryptocurrency market as a viable source of income and investment, similar to the stock market, as the concept of cryptocurrencies continues to gain popularity. Predicting Bitcoin returns is related to financial machine learning, which uses time series to forecast price variance. This study starts with the daily close price of Bitcoin for its initial dataset. The price is transformed into percentages and binary classes, which categorize into “Up” and “Down”, after which a time series is applied to produce two datasets: a categorical dataset for classification and a numerical dataset for regression. For classification that represents a Binary classification in asset-price forecasting, k-fold cross-validation is applied to ensure that the best classifiers are selected for testing and analysis. Most of the regression analysis was based on visualization, which displayed the predicted prices by each regressor in front of the original values and helped analyse the models’ results more accurately. The outcomes of this study were achieved by anticipating bitcoin returns using classification and regression machine learning models, despite the approaches’ low accuracy and significant precision rate to the “Up” class. At this stage, with a significant limitation regarding the dataset and a lack of other indicators, a model capable of predicting future variations is considered a beneficial addition for many trading tools or even for crypto market analysts.

Study and Analysis of Deep Learning Techniques for Solving Financial Problems

Financial markets are competitive environments influenced by several variables and sectors. Wrong decisions can compromise several areas and cause chain reactions that could disrupt various sectors of the economy. In recent years, intelligent models have been used as tools to aid decision-making in financial markets. Deep learning models stand out among them, as they can achieve good generalization with large datasets. The main goal of this paper is to introduce and evaluate deep learning for solving financial problems. We document the process and present the techniques employed to develop models using a dataset containing over 2 million financial data observations. We believe this paper could guide researchers working on similar problems by suggesting resources that can be used and steps that can be followed in similar scenarios, narrowing down the search for efficient financial machine learning models.

Credit Risk Modeling with Graph Machine Learning

Accurate credit ratings are an essential ingredient in the decision-making process for investors, rating agencies, bond portfolio managers, bankers, and policy makers, as well as an important input for risk management and regulation. Credit ratings are traditionally generated from models that use financial statement data and market data, which are tabular (numeric and categorical). Using machine learning methods, we construct a network of firms using U.S. Securities and Exchange Commission (SEC) filings (denoted CorpNet) to enhance the traditional tabular data set with a corporate graph. We show that this generates accurate rating predictions with comparable and better performance to tabular models. We ensemble graph convolutional networks with highly-performant ensembled machine learning models using AutoGluon. This paper demonstrates both transductive and inductive methodologies to extend credit scoring models based on tabular data, which have been used by the ratings industry for decades, to the class of machine learning models on networks. The methodology is extensible to other financial machine learning models that may be enhanced using a corporate graph. History: David Martens served as the senior editor for this article. Data Ethics & Reproducibility Note: No data ethics considerations are foreseen related to this article. The paper deals with corporate credit risk and not consumer credit, which usually entails issues around privacy and bias. The code capsule is available on Code Ocean at https://codeocean.com/capsule/5230264/tree/v2 and in the e-Companion to this article (available at https://doi.org/10.1287/ijds.2022.00018 ).

Option Volatility Investment Strategy: The Combination of Neural Network and Classical Volatility Prediction Model

This study focuses on the volatility prediction and option volatility investment. By investigating the traditional Volatility Prediction Model and machine learning algorithms, this study tries to merge these two aspects together. This work setup a bridge of previous financial studies and machine learning studies by proposing an algorithm integrating neural network and three traditional volatility models, called “Quantile based neural network and model integration combination algorithm.” The algorithm effectively lowers the volatility prediction error (measured by root of mean square error, shorted for RMSE: 0.319724) and beat the Wavenet (RMSE: 0.44) which is the benchmark and surpasses integrated model (RMSE: 0.348346) in test set. In terms of option investment strategy, this paper constructs a CSI 300 index option portfolio which hedges the underlying asset price risk and exposes the volatility risk. Then propose the “Option strategy of volatility prediction with dynamic thresholds.” With the new algorithm above, the strategy improves the return‐risk ratio in test set (measured by Sharpe ratio: 1.99–2.07).

Feature Scaling for Financial Machine Learning

Feature Scaling for Financial Machine Learning

Uncovering feature interdependencies in high-noise environments with stepwise lookahead decision forests

Conventionally, random forests are built from “greedy” decision trees which each consider only one split at a time during their construction. The sub-optimality of greedy implementation has been well-known, yet mainstream adoption of more sophisticated tree building algorithms has been lacking. We examine under what circumstances an implementation of less greedy decision trees actually yields outperformance. To this end, a “stepwise lookahead” variation of the random forest algorithm is presented for its ability to better uncover binary feature interdependencies. In contrast to the greedy approach, the decision trees included in this random forest algorithm, each simultaneously consider three split nodes in tiers of depth two. It is demonstrated on synthetic data and financial price time series that the lookahead version significantly outperforms the greedy one when (a) certain non-linear relationships between feature-pairs are present and (b) if the signal-to-noise ratio is particularly low. A long-short trading strategy for copper futures is then backtested by training both greedy and stepwise lookahead random forests to predict the signs of daily price returns. The resulting superior performance of the lookahead algorithm is at least partially explained by the presence of “XOR-like” relationships between long-term and short-term technical indicators. More generally, across all examined datasets, when no such relationships between features are present, performance across random forests is similar. Given its enhanced ability to understand the feature-interdependencies present in complex systems, this lookahead variation is a useful extension to the toolkit of data scientists, in particular for financial machine learning, where conditions (a) and (b) are typically met.

Explainable fintech lending

Lending to Small and Medium Enterprises (SME) is facilitated by the availability of advanced Machine Learning (ML) methods, embedded in financial technologies, which can accurately predict financial performance from the many data sources available. However, despite their high predictive accuracy, ML models may not provide sufficient explanations to investors and, therefore, may not be adequate for informed decision-making. We propose a financial machine learning model that is both accurate and explainable. To reach this aim, we propose to enhance random forest models with a model selection procedure that progressively removes the least explainable variable, according to the Shapley value method. We apply our proposal to 2,049 SMEs for which yearly financial performance indicators are available. Our results show that both the default and the expected return of SMEs can be well predicted and explained by a small set of indicators deduced from their balance sheets.

A CLOSED-FORM SOLUTION FOR OPTIMAL ORNSTEIN–UHLENBECK DRIVEN TRADING STRATEGIES

When prices reflect all available information, they oscillate around an equilibrium level. This oscillation is the result of the temporary market impact caused by waves of buyers and sellers. This price behavior can be approximated through an Ornstein–Uhlenbeck (OU) process. Market makers provide liquidity in an attempt to monetize this oscillation. They enter a long position when a security is priced below its estimated equilibrium level, and they enter a short position when a security is priced above its estimated equilibrium level. They hold that position until one of three outcomes occur: (1) they achieve the targeted profit; (2) they experience a maximum tolerated loss; (3) the position is held beyond a maximum tolerated horizon. All market makers are confronted with the problem of defining profit-taking and stop-out levels. More generally, all execution traders acting on behalf of a client must determine at what levels an order must be fulfilled. Those optimal levels can be determined by maximizing the trader’s Sharpe ratio in the context of OU processes via Monte Carlo experiments [M. López de Prado (2018) Advances in Financial Machine Learning. Hoboken, NJ, USA: John Wiley & Sons]. This paper develops an analytical framework and derives those optimal levels by using the method of heat potentials [A. Lipton & V. Kaushansky (2018) On the first hitting time density of an Ornstein–Uhlenbeck process, arXiv:1810.02390; A. Lipton & V. Kaushansky (2020a) On the first hitting time density for a reducible diffusion process, Quantitative Finance, doi:10.1080/14697688.2020.1713394].

Can Machines 'Learn' Finance?

Machine learning for asset management faces a unique set of challenges that differ markedly from other domains where machine learning has excelled. Understanding these differences is critical for developing impactful approaches and realistic expectations for machine learning in asset management. We discuss a variety of beneficial use cases and potential pitfalls, and emphasize the importance of economic theory and human expertise for achieving success through financial machine learning.

Valuation Ratios, Surprises, Uncertainty or Sentiment: How Does Financial Machine Learning Predict Returns From Earnings Announcements?

We apply state-of-the-art financial machine learning to assess the return-predictive value of more than 45,000 earnings announcements on a majority of S&P1500 constituents. To represent the diverse information content of earnings announcements, we generate predictor variables based on various sources such as analyst forecasts, earnings press releases and analyst conference call transcripts. We sort announcements into decile portfolios based on the model’s abnormal return prediction. In comparison to three benchmark models, we find that random forests yield superior abnormal returns which tend to increase with the forecast horizon for up to 60 days after the announcement. We subject the model’s learning and out-of-sample performance to further analysis. First, we find larger abnormal returns for small-cap stocks and a delayed return drift for growth stocks. Second, while revenue and earnings surprises are the main predictors for the contemporary reaction, we find that a larger range of variables, mostly fundamental ratios and forecast errors, is used to predict post-announcement returns. Third, we analyze variable contributions and find the model to recover non-linear patterns of common capital markets effects such as the value premium. Leveraging the model’s predictions in a zero-investment trading strategy yields annualized returns of 11.63 percent at a Sharpe ratio of 1.39 after transaction costs.

Separating the signal from the noise – Financial machine learning for Twitter

Most statistical arbitrage strategies in the academic literature solely rely on price time series. By contrast, alternative data sources are of growing importance for professional investors. We contribute to bridging this gap by assessing the price-predictive value of millions of tweets on intraday returns of the S&P 500 constituents from 2014 and 2015. For this purpose, we design a machine learning system addressing specific challenges inherent to this task. At first, building on the literature of financial dictionaries, we engineer domain-specific features along three categories, i.e., directional indicators, relevance indicators and meta features. Next, we leverage a random forest to extract the relationship between these features and subsequent stock returns in a low signal-to-noise setting. For performance evaluation, we run a rigorous event-based backtesting study across all tweets and stocks. We find annualized returns of 6.4 percent and a Sharpe ratio of 2.2 after transaction costs. Finally, we illuminate the machine learning black box and unveil sources of profitability: First, results are both driven and limited by the temporal clustering of tweets, i.e., the majority of profits stem from tweets clustered closely together in time, corresponding to high-event situations. Second, the importance of included features follows an economic rationale, e.g., tweets with positive sentiment tend to yield positive returns and vice versa. Third, we find that stocks of medium market capitalization and from the consumer and technology sectors contribute most to our results, which we interpret as a trade-off between tweet coverage and tweet relevance.

Information leakage in financial machine learning research

Over the past ten years, applications of machine learning research have steadily shown mastery of broader and more complex domains, and the tools to create advanced models have become ubiquitous and more democratized. During that same time, the resources for studying algorithmic finance have also greatly expanded with populous open source communities and more granular time series available to researchers. However, progress in applying machine learning to finance has mostly stagnated, and in some cases regressed. We not only see similar, routine mistakes to those made ten years ago, but the complexity of cutting-edge models and frameworks can easily hide those mistakes. Drawing on both referee reports and published papers, this editorial series will review frequent problems that occur throughout the ML research pipeline which lead to invalid results and unwarranted conclusions.1 The pipeline refers to the series of research stages that are common to all ML projects and independent of any specific machine learning technique or architecture.

Advances in Financial Machine Learning: Numerai's Tournament (Presentation Slides)

Machine learning (ML) is changing virtually every aspect of our lives. Today ML algorithms accomplish tasks that until recently only expert humans could perform. As it relates to finance, this is the most exciting time to adopt a disruptive technology that will transform how everyone invests for generations. In this course, we discuss scientifically sound ML tools that have been successfully applied to the management of large pools of funds. This material is part of Cornell University's ORIE 5256 graduate course at the School of Engineering.

Dissecting Momentum: We Need to Go Deeper

Cross-sectional predictability of returns by past prices, or momentum, is a lasting market anomaly. Previous research reports numerous ways to measure momentum and establishes a multitude of factors predicting its performance. The emerging machine learning asset pricing literature further identifies price-based firm characteristics as major predictors of returns. I investigate predictive power of a broad set of price-based variables over various time horizons in a deep learning framework and document rich non-linear structure in impact of these variables on expected returns in the US equity market. The magnitude and sign of the impact exhibit substantial time variation and are modulated by interaction effects among the variables. The degree of non-linearity in expected returns varies over time and is highest in distressed markets. Incorporating insights from the literature on time-varying, market state-dependent momentum risks and momentum crashes helps to improve out-of-sample performance of neural network portfolios, especially with respect to the downside risk -- investment strategies built on predictions of the deep learning model actively exploit the non-linearities and interaction effects, generating high and statistically significant returns with a robust risk profile and their performance virtually uncorrelated with the established risk factors including momentum. Lastly, I make a case for adoption of automated hyperparameter optimization techniques as an important component of disciplined research in financial machine learning.

Financial Machine Learning Regulation

A look at regulatory challenges and recommendation in the age of AI. Investigating topics like monopoly formation, machine learning auditability, bias mitigation strategies and automated regulatory monitoring.

Ten Applications of Financial Machine Learning

This article reviews ten notable financial applications where ML has moved beyond hype and proven its usefulness. This success does not mean that the use of ML in finance does not face important challenges. The main conclusion is that there is a strong case for applying ML to current financial problems, and that financial ML has a promising future ahead. For a presentation on this topic, see https://ssrn.com/abstract=3197726.

Advances in Financial Machine Learning: Lecture 5/10

Machine learning (ML) is changing virtually every aspect of our lives. Today ML algorithms accomplish tasks that until recently only expert humans could perform. As it relates to finance, this is the most exciting time to adopt a disruptive technology that will transform how everyone invests for generations. In this course, we discuss scientifically sound ML tools that have been successfully applied to the management of large pools of funds.

Advances in Financial Machine Learning: Lecture 4/10

Machine learning (ML) is changing virtually every aspect of our lives. Today ML algorithms accomplish tasks that until recently only expert humans could perform. As it relates to finance, this is the most exciting time to adopt a disruptive technology that will transform how everyone invests for generations. In this course, we discuss scientifically sound ML tools that have been successfully applied to the management of large pools of funds.