mlsanityData to 14 Oct 2026

TopicProphet: Prophesies on Temporal Topic Trends and Stocks

arXiv 2512.11857 ↗First posted 5 Dec 2025cs.LG cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Stocks can't be predicted. Despite many hopes, this premise held itself true for many years due to the nature of quantitative stock data lacking causal logic along with rapid market changes hindering accumulation of significant data for training models. To undertake this matter, we propose a novel framework, TopicProphet, to analyze historical eras that share similar public sentiment trends and historical background. Our research deviates from previous studies that identified impacts of keywords and sentiments - we expand on that method by a sequence of topic modeling, temporal analysis, breakpoint detection and segment optimization to detect the optimal time period for training. This results in improving predictions by providing the model with nuanced patterns that occur from that era's socioeconomic and political status while also resolving the shortage of pertinent stock data to train on. Through extensive analysis, we conclude that TopicProphet produces improved outcomes compared to the state-of-the-art methods in capturing the optimal training data for forecasting financial percentage changes.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 60 references that are in the map. First posted on arXiv 5 Dec 2025.

Builds on

15 of 60 references.

References · 15

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  3. 2023C-Pack: Packed Resources For General Chinese Embeddingscited by 578
  4. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 385
  5. 2018Temporal Relational Ranking for Stock Predictioncited by 102
  6. 2017Latent Dirichlet Allocation (LDA) and Topic modeling: models, applications, a surveycited by 91
  7. 2024AlphaFin: Benchmarking Financial Analysis with Retrieval-Augmented Stock-Chain Frameworkcited by 47
  8. 2024Evaluating Large Language Models on Time Series Feature Understanding: A Comprehensive Taxonomy and Benchmarkcited by 38
  9. 2024Large Language Models Offer an Alternative to the Traditional Approach of Topic Modellingcited by 35
  10. 2024LLMFactor: Extracting Profitable Factors through Prompts for Explainable Stock Movement Predictioncited by 33
  11. 2023Instruction Fusion: Advancing Prompt Evolution through Hybridizationcited by 7
  12. 2020Event-Driven Learning of Systematic Behaviours in Stock Marketscited by 4
3 more
  1. 2024FinBERT-BiLSTM: A Deep Learning Model for Predicting Volatile Cryptocurrency Market Prices Using Market Sentiment Dynamicscited by 1
  2. 2024Exploring applications of topological data analysis in stock index movement predictioncited by 1
  3. 2024Leveraging Large Language Models for Institutional Portfolio Management: Persona-Based Ensemblescited by 1

Built on by

Not cited yet.