Improving Factor-Based Quantitative Investing by Forecasting Company Fundamentals

On a periodic basis, publicly traded companies are required to report fundamentals: financial data such as revenue, operating income, debt, among others. These data points provide some insight into the financial health of a company. Academic research has identified some factors, i.e. computed features of the reported data, that are known through retrospective analysis to outperform the market average. Two popular factors are the book value normalized by market capitalization (book-to-market) and the operating income normalized by the enterprise value (EBIT/EV). In this paper: we first show through simulation that if we could (clairvoyantly) select stocks using factors calculated on future fundamentals (via oracle), then our portfolios would far outperform a standard factor approach. Motivated by this analysis, we train deep neural networks to forecast future fundamentals based on a trailing 5-years window. Quantitative analysis demonstrates a significant improvement in MSE over a naive strategy. Moreover, in retrospective analysis using an industry-grade stock portfolio simulator (backtester), we show an improvement in compounded annual return to 17.1% (MLP) vs 14.4% for a standard factor model.

• Publication year

  2017

• Venue

  arXiv.org

• Publication date

  2017-11-13

• Fields of study

  Mathematics, Business, Economics, Computer Science

• Identifiers
  arXiv 1711.04837
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Recurrent Neural Networks for Multivariate Time Series with Missing Values

  2016cited by this paper
• Investigation Into The Effectiveness Of Long Short Term Memory Networks For Stock Price Prediction

  2016cited by this paper
• Directly Modeling Missing Data in Sequences with RNNs: Improved Classification of Clinical Time Series

  2016cited by this paper
• Context Matters: Refining Object Detection in Video with Recurrent Neural Networks

  2016cited by this paper
• Deep learning for multivariate financial time series

  2015cited by this paper
• Deep Learning for Event-Driven Stock Prediction

  2015cited by this paper
• A LSTM-based method for stock returns prediction: A case study of China stock market

  2015cited by this paper
• Learning to Diagnose with LSTM Recurrent Neural Networks

  2015cited by this paper
• ANN Model to Predict Stock Prices at Stock Exchange Markets

  2014cited by this paper
• Sequence to Sequence Learning with Neural Networks

  2014cited by this paper
• Neural Machine Translation by Jointly Learning to Align and Translate

  2014cited by this paper
• Show and tell: A neural image caption generator

  2014cited by this paper
• Deep Captioning with Multimodal Recurrent Neural Networks (m-RNN)

  2014cited by this paper
• Long-term recurrent convolutional networks for visual recognition and description

  2014cited by this paper
• The Cross Section of Expected Stock Returns

  2014cited by this paper

• Integrating Sentiment Analysis with a Deterministically Optimized Extreme Learning Machine for Stock Market Prediction

  2025cites this paper
• Machine learning-based stock picking using value investing and quality features

  2024cites this paper
• An Exploration of Different Strategies and Applications of Quantitative Investment under Different Models

  2024cites this paper
• Research on Asset Allocation Based on Quantitative Investment

  2024cites this paper
• Forecasting Company Fundamentals

  2024influential citation
• Automated generation of adaptive perturbed images based on GAN for motivated adversaries on deep learning models: Automated generation of adaptive perturbed images based on GAN

  2023cites this paper
• I. MACHINE LEARNING AND DATA SCIENCE APPLICATIONS IN INVESTMENTS HANDBOOK OF ARTIFICIAL INTELLIGENCE AND BIG DATA APPLICATIONS IN INVESTMENTS

  2023cites this paper
• Evaluating Model Performance in Medical Datasets Over Time

  2023cites this paper
• Optimizing Stock Portfolio Performance with a Combined RG1-TOPSIS Model: Insights from the Chinese Market

  2023cites this paper
• Optimizing Investment Strategies with Lazy Factor and Probability Weighting: A Price Portfolio Forecasting and Mean-Variance Model with Transaction Costs Approach

  2023cites this paper
• Can Ensemble Machine Learning Methods Predict Stock Returns for Indian Banks Using Technical Indicators?

  2022cites this paper
• Company investments in the context of financial strategies

  2022cites this paper
• Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes

  2022cites this paper
• Machine Learning Methods for Equity Time Series Forecasting: A Compendium

  2022cites this paper
• Fundamental Analysis of Equity Instruments Using an Entity Embedding Neural Network

  2022cites this paper
• ESG score prediction through random forest algorithm

  2021cites this paper
• Dynamic Virtual Graph Significance Networks for Predicting Influenza

  2021cites this paper
• Real-time forecasting of petrol retail using dilated causal CNNs

  2021cites this paper
• The use of return on equity as a criterion for stock selection in the Indian equity markets

  2021cites this paper
• Forecasting Financial Performance of Companies For Stock Valuation

  2021cites this paper
• Fundamental ratios as predictors of ESG scores: a machine learning approach

  2021cites this paper
• Firm Attributes, Corporate Fundamentals and Investment Strategies: An Empirical Study for Indian Stock Market

  2020cites this paper
• Hyperparameter Optimization for Forecasting Stock Returns

  2020cites this paper
• Mid-Price Stock Prediction with Deep Learning

  2020cites this paper
• Deep Learning for Financial Applications : A Survey

  2020cites this paper
• Machine Learning Algorithms for Financial Asset Price Forecasting

  2020cites this paper
• Artificial Intelligence in Asset Management

  2020cites this paper
• The impact of US sugar prices on the financial performance of US sugar-using firms

  2020cites this paper
• Deeply Equal-Weighted Subset Portfolios

  2020cites this paper
• Disruptive Innovations, Fundamental Strength and Stock Winners: Implications for Stock Index Revisions

  2020cites this paper
• Gazing into the Future: Using Ensemble Techniques to Forecast Company Fundamentals

  2020cites this paper
• Feature Engineering for Mid-Price Prediction With Deep Learning

  2019cites this paper
• Machine Learning for Stock Selection

  2019cites this paper
• Using Deep Learning for Predicting Stock Trends

  2019cites this paper
• Financial series prediction using Attention LSTM

  2019cites this paper
• Generating Adversarial Examples in One Shot With Image-to-Image Translation GAN

  2019cites this paper
• Stock selection with random forest: An exploitation of excess return in the Chinese stock market

  2019cites this paper
• Deep Learning for the Prediction of Stock Market Trends

  2019cites this paper
• Automatic WLAN control using reinforcement learning for improved quality of experience

  2019cites this paper
• Classical and Contemporary Approaches to Big Time Series Forecasting

  2019cites this paper
• A Divide-and-Conquer Framework for Attention-based Combination of Multiple Investment Strategies

  2019cites this paper
• Temporal Relational Ranking for Stock Prediction

  2018cites this paper
• A Practical Machine Learning Approach for Dynamic Stock Recommendation

  2018cites this paper
• Predicció del preu de criptomonedes utilitzant tècniques de Deep Learning

  2018cites this paper
• Using Alternative and Big Data to Trade Macro Assets

  2018cites this paper
• Machine learning-aided modeling of fixed income instruments

  2018cites this paper
• Multimodal deep learning for short-term stock volatility prediction

  2018cites this paper
• Robust Classification of Financial Risk

  2018cites this paper
• Deep Reinforcement Learning

  2018cites this paper