Learning Mutual Fund Categorization using Natural Language Processing

TL;DR

This paper demonstrates that mutual fund categorization can be effectively learned from unstructured text data using NLP models, achieving high accuracy in classifying funds into Lipper categories.

Contribution

It introduces a novel approach to fund categorization directly from unstructured descriptions, bypassing traditional structured data reliance, and evaluates various NLP models for this task.

Findings

High accuracy in fund categorization using NLP models

Unstructured investment strategy descriptions are sufficient for classification

Limitations identified in pre-trained NLP architectures for this task

Abstract

Categorization of mutual funds or Exchange-Traded-funds (ETFs) have long served the financial analysts to perform peer analysis for various purposes starting from competitor analysis, to quantifying portfolio diversification. The categorization methodology usually relies on fund composition data in the structured format extracted from the Form N-1A. Here, we initiate a study to learn the categorization system directly from the unstructured data as depicted in the forms using natural language processing (NLP). Positing as a multi-class classification problem with the input data being only the investment strategy description as reported in the form and the target variable being the Lipper Global categories, and using various NLP models, we show that the categorization system can indeed be learned with high accuracy. We discuss implications and applications of our findings as well as limitations of existing pre-trained architectures in applying them to learn fund categorization.