Hybrid recommender for computer aided design software

Abstract

Choosing the right computer-aided design (CAD) software is a complex task due to the wide variety of available options. Using user opinions and reviews may not be sufficient, which highlighting the need for a decision support system. In this paper, we develop and evaluate a hybrid recommendation program (HRP) for CAD software written in the Python programming language, combining collaborative filtering (CF) and content-based filtering (CBF) using k-nearest neighbors (KNN). CF uses user ratings to identify similar users, while CBF compares software characteristics to find similar options. In our hybrid approach, we integrate both filtering techniques with KNN to generate personalized recommendations. It will improve the relevance of software options, help users make choices (students, educators, and professionals), and encourage the adoption of tools most appropriate for every profile. We used the analytic hierarchy process (AHP) method to choose the criteria for our recommendation program. We tested the HRP on a simulated CAD dataset and found that it made recommendations much more accurately than using CF and CBF separately. Evaluation metrics like precision (0.81), recall (0.95), and F1-score (0.87) show that this hybrid approach works, making it a more reliable tool for helping people choose CAD software.