Paper: arXiv 2401.07483
Authors: Partha Sen, Sumana Sen
Abstract
Design/methodology/approach This research evaluated the databases of SQL, No-SQL and graph databases to compare and contrast efficiency and performance. To perform this experiment the data were collected from multiple sources including stock price and financial news. Python is used as an interface to connect and query databases (to create database structures according to the feed file structure, to load data into tables, objects, to read data , to connect PostgreSQL, ElasticSearch, Neo4j. Purpose Modern applications of LLM (Large language model) including RAG (Retrieval Augmented Generation) with Machine Learning, deep learning, NLP (natural language processing) or Decision Analytics are computationally expensive. Finding a better option to consume less resources and time to get the result. Findings The Graph database of ESG (Environmental, Social and Governance) is comparatively better and can be considered for extended analytics to integrate ESG in business and investment. Practical implications A graph ML with a RAG architecture model can be introduced as a new framework with less computationally expensive LLM application in the equity filtering process for portfolio management. Originality/value Filtering out selective stocks out of two thousand or more listed companies in any stock exchange for active investment, consuming less resource consumption especially memory and energy to integrate artificial intelligence and ESG in business and investment.
Complexity vs Empirical Score
- Math Complexity: 2.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper focuses on practical database implementation (SQL, NoSQL, Graph) with Python code and performance metrics (response time, CPU usage) on real financial data, giving it high empirical rigor. However, it lacks advanced mathematical derivations or heavy statistical theory, relying more on applied technology comparisons.
Research Flowchart
flowchart TD A["Research Goal: Find computationally efficient method for ESG equity filtering in investment management"] --> B["Methodology: Comparative Evaluation of Databases"] B --> C["Data Inputs: Stock Prices & Financial News"] C --> D["Computational Process: Python Interface connecting to<br>SQL, No-SQL (ElasticSearch), & Graph (Neo4j)"] D --> E["Analysis: Compare efficiency & performance"] E --> F["Key Finding: Graph Databases (Neo4j) offer best performance"] F --> G["Outcome: Proposed Graph ML RAG Framework<br>for low-resource ESG Equity Filtering"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes a graph‑ML with a Retrieval‑Augmented Generation (RAG) architecture as a new framework for ESG‑integrated equity filtering that is less computationally expensive than large language model approaches.
Source sentence
Practical implications A graph ML with a RAG architecture model can be introduced as a new framework with less computationally expensive LLM application in the equity filtering process for portfolio management.
Assumes
No explicit assumptions found in the text.
Data
- stock price data market-prices unknown
Source sentence
Loading of two months stock price data for different stocks done by reading multiple CSV files and combining them in python.
- news articles text-news unknown
Source sentence
Loading the two months of news articles extracted in python using googlenews package from various news articles with a format of portal name, date and content from the file and put that in the dataframe.
Costs
Not applicable
Finds 3
- The Graph database of ESG is comparatively better and can be considered for extended analytics to integrate ESG in business and investment. performance
Source sentence
Findings The Graph database of ESG (Environmental, Social and Governance) is comparatively better and can be considered for extended analytics to integrate ESG in business and investment.
- Neo4j is performing significantly better in terms of response time (measured in milliseconds) for news search. performance
Source sentence
Results Neo4j is performing significantly better (Appendix 3) in terms of response time (measured in milliseconds) for News Search.
- Neo4j's superior performance in response time and CPU usage underscores its optimization for handling complex, interconnected data in ESG‑integrated equity filtering. performance
Source sentence
Neo4j's superior performance in terms of response time and CPU usage underscores its optimization for handling complex, interconnected data.
Checked by others
No other paper in the archive has been found to support or contradict these findings (compared with 10 related papers). Coverage is partial, so this is neither replication nor refutation.
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.