Industry Classification Using a Novel Financial Time-Series Case Representation

Paper: arXiv 2305.00245

Authors: Rian Dolphin, Barry Smyth, Ruihai Dong

Abstract

The financial domain has proven to be a fertile source of challenging machine learning problems across a variety of tasks including prediction, clustering, and classification. Researchers can access an abundance of time-series data and even modest performance improvements can be translated into significant additional value. In this work, we consider the use of case-based reasoning for an important task in this domain, by using historical stock returns time-series data for industry sector classification. We discuss why time-series data can present some significant representational challenges for conventional case-based reasoning approaches, and in response, we propose a novel representation based on stock returns embeddings, which can be readily calculated from raw stock returns data. We argue that this representation is well suited to case-based reasoning and evaluate our approach using a large-scale public dataset for the industry sector classification task, demonstrating substantial performance improvements over several baselines using more conventional representations.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.5/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper presents a pragmatic empirical approach to industry classification using time-series stock return embeddings within a case-based reasoning framework. While the mathematical formulations are accessible rather than deep, the empirical setup leverages a large-scale public dataset to demonstrate clear performance gains over standard representations.

Research Flowchart

  flowchart TD
    A[Research Goal: Improve Industry Sector Classification using CBR] --> B[Data Input: Historical Stock Returns Time-Series Data]
    B --> C[Methodology: Transform Raw Returns into Stock Returns Embeddings]
    C --> D[CBR Pipeline: Case Representation & Similarity Matching]
    D --> E[Evaluation: Benchmark against Conventional Representations]
    E --> F[Key Outcome: Superior Classification Performance over Baselines]