Instruction-Based Fine-tuning of Open-Source LLMs for Predicting Customer Purchase Behaviors

TL;DR

This paper demonstrates that instruction fine-tuning large language models like Mistral with LoRA significantly improves their ability to predict customer purchase behaviors from financial transaction data, outperforming traditional models.

Contribution

It introduces a novel application of instruction fine-tuning with LoRA to adapt open-source LLMs for financial transaction prediction tasks, showing superior performance.

Findings

Fine-tuned Mistral outperforms traditional models in F1 scores.

Model better predicts minority classes in transaction data.

Enhanced semantic understanding improves prediction accuracy.

Abstract

In this study, the performance of various predictive models, including probabilistic baseline, CNN, LSTM, and finetuned LLMs, in forecasting merchant categories from financial transaction data have been evaluated. Utilizing datasets from Bank A for training and Bank B for testing, the superior predictive capabilities of the fine-tuned Mistral Instruct model, which was trained using customer data converted into natural language format have been demonstrated. The methodology of this study involves instruction fine-tuning Mistral via LoRA (LowRank Adaptation of Large Language Models) to adapt its vast pre-trained knowledge to the specific domain of financial transactions. The Mistral model significantly outperforms traditional sequential models, achieving higher F1 scores in the three key merchant categories of bank transaction data (grocery, clothing, and gas stations) that is crucial for targeted marketing campaigns. This performance is attributed to the model's enhanced semantic understanding and adaptability which enables it to better manage minority classes and predict transaction categories with greater accuracy. These findings highlight the potential of LLMs in predicting human behavior.