# Improving Requirements Classification with SMOTE-Tomek Preprocessing

arXiv: https://arxiv.org/abs/2501.06491 · HTML: https://mlsanity.com/paper/2501.06491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 45 references that are in the map.
- First posted on arXiv 11 Jan 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SAGA: A Fast Incremental Gradient Method With Support for Non-Strongly Convex Composite Objectives](https://mlsanity.com/paper/1407.0202/) (2014)
- [Requirements Engineering Challenges in Building AI-Based Complex Systems](https://mlsanity.com/paper/1908.11791/) (2019)
- [Learning Car Speed Using Inertial Sensors for Dead Reckoning Navigation](https://mlsanity.com/paper/2205.07883/) (2022)
- [Deep Learning for Inertial Sensor Alignment](https://mlsanity.com/paper/2212.11120/) (2022)
- [A Machine Learning Approach for Hierarchical Classification of Software Requirements](https://mlsanity.com/paper/2302.12599/) (2023)

## Abstract (arXiv)

This study emphasizes the domain of requirements engineering by applying the SMOTE-Tomek preprocessing technique, combined with stratified K-fold cross-validation, to address class imbalance in the PROMISE dataset. This dataset comprises 969 categorized requirements, classified into functional and non-functional types. The proposed approach enhances the representation of minority classes while maintaining the integrity of validation folds, leading to a notable improvement in classification accuracy. Logistic regression achieved 76.16%, significantly surpassing the baseline of 59.85%. These results highlight the applicability and efficiency of machine learning models as scalable and interpretable solutions.