Signal-based Trading on SPY [ETF]

Xiangrong Zhao

doi:10.47297/wspceWSP2516-251924.20261002

PDF
导出
分享
收藏
专辑

10卷第2期

浏览量: 0 Downloads: 0

Signal-based Trading on SPY [ETF]
Signal-based Trading on SPY [ETF]
Dongbei University of Finance and Economics, Dalian, Liaoning, 116021, China
2026年10卷第2期页码：119-122
纸质出版：2026-04-30
DOI：10.47297/wspceWSP2516-251924.20261002
Accepted：

Scan QR Code

Xiangrong Zhao. (2026). Signal-based Trading on SPY [ETF]. 创意经济（英文版）, 10(2), 119-122.

Zhao Xiangrong.Signal-based Trading on SPY [ETF][J].Creative Economy,2026,10(02):119-122.
Xiangrong Zhao. (2026). Signal-based Trading on SPY [ETF]. 创意经济（英文版）, 10(2), 119-122. DOI： 10.47297/wspceWSP2516-251924.20261002.

Zhao Xiangrong.Signal-based Trading on SPY [ETF][J].Creative Economy,2026,10(02):119-122. DOI： 10.47297/wspceWSP2516-251924.20261002.

摘要

Abstract

This study constructs a signal-based trading strategy for the SPDR S&P 500 ETF Trust (SPY) using a multiple linear regression (MLR) model and data from major global market indices

including the Nikkei Index

CAC40 Index

Dow Jones Industrial Average

S&P 500 Index

and Australian All Ordinaries Index. The predictive model is estimated via Ordinary Least Squares and evaluated using R-squared and Root Mean Squared Error (RMSE). Based on the return prediction signals generated by the regression model

a dynamic signal-driven trading strategy is developed and compared against a buy-and-hold benchmark. The strategy performance is assessed through the Sharpe Ratio and Maximum Drawdown (MDD). Empirical results reveal that the MLR model exhibits extremely low explanatory power

with R-squared values of approximately 0.009 for the training set and 0.012 for the test set

indicating a weak linear relationship between selected global indices and SPY returns. Furthermore

the RMSE increases sharply from 1.55 in-sample to 3.51 out-of-sample

suggesting significant overfitting. While the signal-driven strategy outperforms the benchmark during the training period with a Sharpe Ratio of 1.09 and an MDD of 12.48%

its performance deteriorates substantially in the test set

with the Sharpe Ratio plummeting to 0.34 and the MDD escalating to 40.75%. These findings demonstrate severe overfitting issues and highlight the practical limitations of simple linear regression-based active trading strategies compared to passive investment approaches.

关键词

Keywords

references

Andrew, A. (2014) Asset Management: A Systematic Approach to Factor Investing . OUP .

Bacon, C.R. (2008) Practical Portfolio Performance Measurement and Attribution (2nd ed .). Wiley Publishers .

Base S. & Humbe V. ( 2024) Python-Powered ETF Trading: Unleashing Algorithmic Trading Strategies . 2024 3rd Edition of IEEE Delhi Section Flagship Conference , 21 November 2024.

Box G. E. P. , & Jenkins G. M. ( 1976) Time Series Analysis: Forecasting and Control . Wiley Publishers .

Chekhov A. , Uryasev S. & Zabarankin M. ( 2005) DRAWDOWN MEASURE IN PORTFOLIO OPTIMIZATION . International Journal of Theoretical & Applied Finance , 8 ( 1 ), 13 .

Chen H. 2024) Active mutual funds and their passive ETF investments . Journal of Financial Research , 47 ( 2 ), 367 .

Fama E. F. , & French K. R. ( 1993) Common risk factors in the returns on stocks and bonds . Journal of Financial Economics .

Hyndman R.J. & Koehler A.B. ( 2006) Another look at measures of forecast accuracy . International Journal of Forecasting , 22 ( 4 ), 679 .

Laborda J. , Laborda R. & de la Cruz J. ( 2024) Can ETFs affect U.S. financial stability? A quantile cointegration analysis . Financial Innovation , 10 , 1 - 24 .

Joshi G. & Dash R.K. ( 2024) Exchange-traded funds and the future of passive investments: a bibliometric review and future research agenda . Future Business Journal , 10 ( 1 ), 1 - 21 .

Laughlin, L.S. ( 2016 ) America's Most Popular Investment May Be Toxic . Available from : https://openurl.ebsco.com/EPDB%3Absu%3A9%3A8588249/detailv2?sid=ebsco %3Aplink%3Acrawler&id=ebsco%3Absu%3A112396099&crl=f&link_origin=none (Accessed 26 December 2025 https://openurl.ebsco.com/EPDB%3Absu%3A9%3A8588249/detailv2?sid=ebsco%3Aplink%3Acrawler&id=ebsco%3Absu%3A112396099&crl=f&link_origin=none(Accessed26December2025 ]

Lo , A. & MacKinlay, A.C. ( 1900) Data-Snooping Biases in Tests of Financial Asset Pricing Models . The Review of Financial Studies , 3 ( 3 ), 431 - 467 .

Magdon-Ismail M. , Aliya , A. & Abu-Mostafa, Y. ( 2003) The maximum drawdown of the Brownian motion . 2003 IEEE International Conference on Computational Intelligence for Financial Engineering , 2003 .

Malhotra , P. (2024) The rise of passive investing: a systematic literature review applying PRISMA framework . Journal of Capital Markets Studies , 8 ( 1 ), 95 .

Pace D. , Hili J. , & Grima S. ( 2016) Active versus passive investing: An empirical study on the US and European mutual funds and ETFs . In Contemporary Issues in Bank Financial Management. Available https://research.ebsco.com/c/462pgp/search/details/orhxdi5xbz?db=edsemr https://research.ebsco.com/c/462pgp/search/details/orhxdi5xbz?db=edsemr [Accessed 26 December 2025 ]

Poutachidou , N. & Koulis, A. ( 2025) The Investment Styles and Performance of AI Related ETFs: Analyzing the Impact of Active Management . FintTech , 4 ( 2 ), 20 .

Sharpe , W. F. (1994) The Sharpe Ratio . The Journal of Portfolio Management .