Time Series Analysis in American Stock Market Recovering in Post COVID-19 Pandemic Period

Paper: arXiv 2212.05369

Authors: Weilin Fu, Zhuoran Li, Yupeng Zhang, Xingyou Zhou

Abstract

Every financial crisis has caused a dual shock to the global economy. The shortage of market liquidity, such as default in debt and bonds, has led to the spread of bankruptcies, such as Lehman Brothers in 2008. Using the data for the ETFs of the S&P 500, Nasdaq 100, and Dow Jones Industrial Average collected from Yahoo Finance, this study implemented Deep Learning, Neuro Network, and Time-series to analyze the trend of the American Stock Market in the post-COVID-19 period. LSTM model in Neuro Network to predict the future trend, which suggests the US stock market keeps falling for the post-COVID-19 period. This study reveals a reasonable allocation method of Long Short-Term Memory for which there is strong evidence.

Complexity vs Empirical Score

• Math Complexity: 2.0/10
• Empirical Rigor: 2.5/10
• Quadrant: Philosophers — conceptual discussion, limited math and data

Why this score: The paper applies standard off-the-shelf LSTM models to public ETF data without significant mathematical depth or robust empirical methodology. It lacks novel insights, rigorous out-of-sample testing, or sophisticated financial modeling beyond basic time-series forecasting.

Research Flowchart

  flowchart TD
    A[Goal: Predict US Stock Market Trend Post-COVID-19] --> B[Data Collection: Yahoo Finance ETFs<br>S&P 500, Nasdaq 100, Dow Jones]
    B --> C[Methodology: Deep Learning & Time-Series Analysis]
    C --> D[Computational Model: Long Short-Term Memory - LSTM]
    D --> E[Outcome: US Stock Market Predicted to Keep Falling]
    D --> F[Outcome: Established Optimal LSTM Allocation Strategy]