• Corpus ID: 220403470

Uncertainty-Aware Lookahead Factor Models for Quantitative Investing

  title={Uncertainty-Aware Lookahead Factor Models for Quantitative Investing},
  author={Lakshay Chauhan and John Alberg and Zachary Chase Lipton},
On a periodic basis, publicly traded companies report fundamentals, financial data including revenue, earnings, debt, among others. Quantitative finance research has identified several factors, functions of the reported data that historically correlate with stock market performance. In this paper, we first show through simulation that if we could select stocks via factors calculated on future fundamentals (via oracle), that our portfolios would far outperform standard factor models. Motivated… 

Figures and Tables from this paper

Quantitative Stock Investment by Routing Uncertainty-Aware Trading Experts: A Multi-Task Learning Approach
AlphaMix is a novel two-stage mixture-of-experts (MoE) framework for quantitative investment to mimic the efficient bottom-up trading strategy design workflow of successful trading firms and is a universal framework that is applicable to various backbone network architectures with consistent performance gains.
Learning Multiple Stock Trading Patterns with Temporal Routing Adaptor and Optimal Transport
A novel architecture, Temporal Routing Adaptor (TRA), is proposed to empower existing stock prediction models with the ability to model multiple stock trading patterns and design a learning algorithm based on Optimal Transport to obtain the optimal sample to predictor assignment and effectively optimize the router with such assignment through an auxiliary loss term.
Volatility Based Kernels and Moving Average Means for Accurate Forecasting with Gaussian Processes
A new class of models are introduced, Volt and Magpie, that significantly outperform baselines in stock and wind speed forecasting, and naturally extend to the multitask setting.
Reinforcement Learning for Quantitative Trading
A taxonomy of RL-based QT models is devised, along with a comprehensive summary of the state of the art, and current challenges and proposed future research directions in this exciting field are discussed.


Factor-Based Investing: The Long-Term Evidence
Factor investing is popular, and its adoption is accelerating. One reason it is increasingly being embraced is that portfolio return expectations seem to be evidence based. However, much of the
ANN Model to Predict Stock Prices at Stock Exchange Markets
The research proposes the use of Artificial Neural Network that is feedforward multi-layer perceptron with error backpropagation and develops a model of configuration 5:21: 21:1 with 80% training data in 130,000 cycles capable of prediction on typical stock markets.
High frequency trading strategies, market fragility and price spikes: an agent based model perspective
A novel agent-based simulation for exploring algorithmic trading strategies is proposed and is able to reproduce a number of stylised market properties including: clustered volatility, autocorrelation of returns, long memory in order flow, concave price impact and the presence of extreme price events.
Trade Execution Costs and Market Quality after Decimalization
Abstract This study assesses trade execution costs and market quality for NYSE and Nasdaq stocks before and after the 2001 change to decimal pricing. Several theoretical predictions are confirmed.
Which News Moves Stock Prices? A Textual Analysis
A basic tenet of financial economics is that asset prices change in response to unexpected fundamental information. Since Roll's (1988) provocative presidential address that showed little relation
The Cross Section of Expected Stock Returns
This paper studies the cross-sectional properties of return forecasts derived from Fama-MacBeth regressions. These forecasts mimic how an investor could, in real time, combine many firm
Analysis of Stock Price Movement Following Financial News Article Release
What effect does a financial news article have on stock price? To answer this question we investigate stock price movements within the minutes following financial news releases, broken down by media
Deep Learning for Event-Driven Stock Prediction
This work proposes a deep learning method for event-driven stock market prediction that can achieve nearly 6% improvements on S&P 500 index prediction and individual stock prediction, respectively, compared to state-of-the-art baseline methods.
Deep learning for multivariate financial time series
The results obtained from the deep neural network are better and more stable than the benchmarks and support that deep learning methods will find their way in finance due to their reliability and good performance.
Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network Model
Empirical results show that the Type 2 input variables can generate a higher forecast accuracy and that it is possible to enhance the performance of the optimized ANN model by selecting input variables appropriately.