Artificial Intelligence for ETF Market Prediction and Portfolio Optimization

  title={Artificial Intelligence for ETF Market Prediction and Portfolio Optimization},
  author={Min-Yuh Day and Jian-Ting Lin},
  journal={2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)},
  • Min-Yuh Day, Jian-Ting Lin
  • Published 1 August 2019
  • Computer Science
  • 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM)
In asset allocation and time-series forecasting studies, few have shed light on using the different machine learning and deep learning models to verify the difference in the result of investment returns and optimal asset allocation. To fill this research gap, we develop a robo-advisor with different machine learning and deep learning forecasting methodologies and utilize the forecasting result of the portfolio optimization model to support our investors in making decisions. This research… Expand
Neural network with fixed noise for index-tracking portfolio optimization
This work proposes a deep learning framework to optimize the index-tracking portfolio and uses the output distribution of the softmax layer from the fixed noise as the portfolio weights and verifies the tracking performance of the proposed method on the S&P 500 index. Expand
A framework for utilizing stock trend prediction outputs in stock selection and portfolio optimization
In this paper, we develop a framework for using stock trend prediction outputs, which we generate using long short-term memory (LSTM) deep neural networks, in both stock selection and portfolioExpand
Robo-Advisors: Machine Learning in Trend-Following ETF Investments
An application of machine learning to exchange traded fund investments in the U.S. market is examined and a predictive support vector machine model that can detect long or short investment signals is built, finding that the high probability of an upward momentum from the forecasting model suggests a long exchange trade fund signal, whereas the low probability of a downward momentum indicates a short exchange trade signal. Expand
A Long Short-Term Memory Approach Towards Stock Selection and Portfolio Optimization
This paper uses LSTM networks to predict the direction of stock movement and a stock price proxy measure, and uses these in stock selection and within the Markowitz mean-variance portfolio optimization framework. Expand
Intraday Market Predictability: A Machine Learning Approach
Conducting, to our knowledge, the largest study ever of five-minute equity market returns using state-of-the-art machine learning models trained on the cross-section of lagged market indexExpand
Adversarial Attacks Against Reinforcement Learning-Based Portfolio Management Strategy
This research proposes an extension of the ensemble of the identical independent evaluators (EIIE) method, called enhanced EIIE, in which information on the best bids and asks is incorporated, and applies it to an adversary used to attack an RL-based trading agent. Expand


Which Artificial Intelligence Algorithm Better Predicts the Chinese Stock Market?
It is found that the deep learning method of predicting stock index futures outperforms the back propagation, the extreme learning machine, and the radial basis function neural network in its fitting degree and directional predictive accuracy, and that increasing the amount of data increases predictive performance. Expand
Time series analysis, forecasting and control
This revision of a classic, seminal, and authoritative book explores the building of stochastic models for time series and their use in important areas of application —forecasting, model specification, estimation, and checking, transfer function modeling of dynamic relationships, modeling the effects of intervention events, and process control. Expand
A Multivariate GARCH Model of International Transmissions of Stock Returns and Volatility: The Case of the United States and Canada
This study examines the short-run dynamics of returns and volatility for stocks traded on the New York and Toronto stock exchanges. The main finding is that inferences about the magnitude andExpand
Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation
Traditional econometric models assume a constant one-period forecast variance. To generalize this implausible assumption, a new class of stochastic processes called autoregressive conditionalExpand
Deep Learning
Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data. Expand
ImageNet classification with deep convolutional neural networks
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective. Expand
Long Short-Term Memory
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Expand
XGBoost: A Scalable Tree Boosting System
This paper proposes a novel sparsity-aware algorithm for sparse data and weighted quantile sketch for approximate tree learning and provides insights on cache access patterns, data compression and sharding to build a scalable tree boosting system called XGBoost. Expand
Fintech: Ecosystem, business models, investment decisions, and challenges
Fintech brings about a new paradigm in which information technology is driving innovation in the financial industry. Fintech is touted as a game changing, disruptive innovation capable of shaking upExpand
Support-Vector Networks
High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition. Expand