Enhancing literature review with LLM and NLP methods. Algorithmic trading case

Paper: arXiv 2411.05013

Abstract

This study utilizes machine learning algorithms to analyze and organize knowledge in the field of algorithmic trading. By filtering a dataset of 136 million research papers, we identified 14,342 relevant articles published between 1956 and Q1 2020. We compare traditional practices-such as keyword-based algorithms and embedding techniques-with state-of-the-art topic modeling methods that employ dimensionality reduction and clustering. This comparison allows us to assess the popularity and evolution of different approaches and themes within algorithmic trading. We demonstrate the usefulness of Natural Language Processing (NLP) in the automatic extraction of knowledge, highlighting the new possibilities created by the latest iterations of Large Language Models (LLMs) like ChatGPT. The rationale for focusing on this topic stems from our analysis, which reveals that research articles on algorithmic trading are increasing at a faster rate than the overall number of publications. While stocks and main indices comprise more than half of all assets considered, certain asset classes, such as cryptocurrencies, exhibit a much stronger growth trend. Machine learning models have become the most popular methods in recent years. The study demonstrates the efficacy of LLMs in refining datasets and addressing intricate questions about the analyzed articles, such as comparing the efficiency of different models. Our research shows that by decomposing tasks into smaller components and incorporating reasoning steps, we can effectively tackle complex questions supported by case analyses. This approach contributes to a deeper understanding of algorithmic trading methodologies and underscores the potential of advanced NLP techniques in literature reviews.

Complexity vs Empirical Score

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

Why this score: The paper focuses on methodological application of NLP/LLMs for literature review, presenting conceptual trends rather than novel mathematical derivations or backtested trading strategies.

Research Flowchart

  flowchart TD
  A["Research Goal: Analyze & Organize<br>Algorithmic Trading Literature"] --> B["Data Input: 136M Research Papers<br>(Filtered to 14,342 Relevant Articles)"]
  B --> C["Methodology: Compare Approaches<br>Keyword vs. Embeddings vs. Topic Modeling"]
  C --> D["Computational Process: NLP & LLMs<br>for Knowledge Extraction & Analysis"]
  D --> E["Outcome 1: ML Models Identified<br>as Dominant & Growing Method"]
  D --> F["Outcome 2: Strong Growth in<br>Cryptocurrency & Cross-Asset Research"]
  D --> G["Outcome 3: LLMs Enable<br>Complex Reasoning & Task Decomposition"]
  E --> H["Final Contribution: Enhanced Literature Review<br>Revealing Method Evolution & Trends"]
  F --> H
  G --> H

Cited References (34)

1. Using Machine Learning and Natural Language Processing to Review and Classify the Medical Literature on Cancer Susceptibility Genes (2019)
2. Using Machine Learning and Natural Language Processing to Review and Classify the Medical Literature on Cancer Susceptibility Genes (2019)
3. Media-expressed tone, option characteristics, and stock return predictability (2022) — link
4. ChatGPT for (Finance) research: The Bananarama Conjecture (2023) — link
5. O ver-optimization of academic publishing metrics: observing G oodhart’s L aw in action (2019) — link
6. Machine learning techniques applied to construction: A hybrid bibliometric analysis of advances and future directions (2022) — link
7. BERTopic: Neural topic modeling with a class-based TF-IDF procedure (2022) — link
8. ScholarBERT: Bigger is Not Always Better (2022) — link

0 of 34 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.