Predicting S&P 500 Index ETF (SPY) During COVID-19 via K-Nearest Neighbors (KNN) Algorithm

In this paper, the daily adjusted closing price of SPY (SPDR S&P 500 ETF Trust) is predicted by using High-Low prices SPY, DIA Dow Jones Industrial Average Trust), and QQQ (Invesco NASDAQ-100 via KNN method during COVID-19 pandemic period. Results show that applying method, a simple, intuitive, explainable machine learning feasible effective in prediction corresponding trade decisions pandemic. Experiments also indicate adding information on from (a value tilt ETF) growth cannot improve accuracy both trading decisions. are consistent with previous findings based portfolio approach spread does not help predict stock market returns.