Towards Dynamic Feature Selection with Attention to Assist Banking Customers in Establishing a New Business

TL;DR

This paper proposes an attention-based supervised feature selection framework to identify key features from diverse data sources, aiding banking customers in establishing new businesses by uncovering relevant patterns and correlations.

Contribution

It introduces a novel attention-based feature selection method specifically designed for integrating banking and non-banking data in the context of new business establishment.

Findings

Effective identification of important features from heterogeneous data sources

Improved feature relevance for customer queries about starting a business

Validated approach on publicly available datasets

Abstract

Establishing a new business may involve Knowledge acquisition in various areas, from personal to business and marketing sources. This task is challenging as it requires examining various data islands to uncover hidden patterns and unknown correlations such as purchasing behavior, consumer buying signals, and demographic and socioeconomic attributes of different locations. This paper introduces a novel framework for extracting and identifying important features from banking and non-banking data sources to address this challenge. We present an attention-based supervised feature selection approach to select important and relevant features which contribute most to the customer's query regarding establishing a new business. We report on the experiment conducted on an openly available dataset created from Kaggle and the UCI machine learning repositories.