ETF Portfolio Construction via Neural Network trained on Financial Statement Data
This work addresses the challenge of managing ETFs with limited historical data, such as thematic ETFs, for asset managers, though it is incremental as it adapts existing neural network techniques to a specific financial domain.
The paper tackles the data shortage problem in applying deep neural networks to ETF portfolio management by training neural networks on individual stock financial data to predict stock performance and then constructing ETF portfolios using these predictions and portfolio deposit files. The proposed method outperforms baselines in experiments.
Recently, the application of advanced machine learning methods for asset management has become one of the most intriguing topics. Unfortunately, the application of these methods, such as deep neural networks, is difficult due to the data shortage problem. To address this issue, we propose a novel approach using neural networks to construct a portfolio of exchange traded funds (ETFs) based on the financial statement data of their components. Although a number of ETFs and ETF-managed portfolios have emerged in the past few decades, the ability to apply neural networks to manage ETF portfolios is limited since the number and historical existence of ETFs are relatively smaller and shorter, respectively, than those of individual stocks. Therefore, we use the data of individual stocks to train our neural networks to predict the future performance of individual stocks and use these predictions and the portfolio deposit file (PDF) to construct a portfolio of ETFs. Multiple experiments have been performed, and we have found that our proposed method outperforms the baselines. We believe that our approach can be more beneficial when managing recently listed ETFs, such as thematic ETFs, of which there is relatively limited historical data for training advanced machine learning methods.