GenAI for Investment Recommendations Using RSS Feed
Bibliographic record
Abstract
This study presents the design and implementation of an advanced financial news analysis system aimed at providing real-time insights and responses to user queries. The system utilizes a multi-step pipeline that involves fetching live RSS (Really Simple Syndication) feed data from multiple sources, processing and categorizing the data, and applying natural language processing (NLP) techniques, such as named entity recognition (NER) and sentiment analysis, to extract and understand relevant information. To respond to user interactions, the system leverages LangChain and ChatGroq to generate contextually appropriate responses using a large language model (LLM). The resulting interface, built with Streamlit, facilitates intuitive user interaction and the seamless display of generated insights. Evaluation results demonstrate the system's high accuracy in categorizing news articles (average accuracy of 92%) and efficient response times for generating outputs (average response time of 4.75 seconds). The system's ability to handle incremental data updates, categorize news into relevant financial topics, and generate rapid, AI-driven responses makes it a powerful tool for financial analysis and decision-making.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".