Paper: arXiv 2409.08297

Abstract

In recent years, financial analysts have been trying to develop models to predict the movement of a stock price index. The task becomes challenging in vague economic, social, and political situations like in Pakistan. In this study, we employed efficient models of machine learning such as long short-term memory (LSTM) and quantum long short-term memory (QLSTM) to predict the Karachi Stock Exchange (KSE) 100 index by taking monthly data of twenty-six economic, social, political, and administrative indicators from February 2004 to December 2020. The comparative results of LSTM and QLSTM predicted values of the KSE 100 index with the actual values suggested QLSTM a potential technique to predict stock market trends.

Complexity vs Empirical Score

  • Math Complexity: 7.0/10
  • Empirical Rigor: 6.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced machine learning techniques (LSTM and Quantum LSTM) involving complex model architectures and sequential data processing, indicating high mathematical density. It is empirical in nature, using a substantial dataset of 26 indicators over 16 years for a specific market (KSE 100), with comparative results suggesting practical applicability, though it lacks detailed backtesting or code implementation.

Research Flowchart

  flowchart TD
  A["Research Goal: Predict KSE 100 Index<br/>using Economic, Social, Political Data"] --> B["Data Collection & Preprocessing<br/>26 Indicators (2004-2020)"]
  B --> C["Feature Engineering & Splitting"]
  C --> D["Model Training"]
  D --> D1["LSTM<br/>Recurrent Neural Network"]
  D --> D2["QLSTM<br/>Quantum-Recurrent Network"]
  D1 & D2 --> E["Testing & Evaluation"]
  E --> F["Key Findings"]
  F --> F1["QLSTM outperforms LSTM"]
  F --> F2["QLSTM captures non-linear trends better"]
  F --> F3["Potential for volatile markets"]