What the study found
The study found that a hybrid recommendation system for interior design services performed best among the models tested. The logistic regression-based hybrid model achieved the strongest overall result, with an accuracy of 83.62%.
Why the authors say this matters
The authors say the study helps improve personalization and accessibility in the interior design sector through machine learning-enabled recommendation systems. They also suggest it can bridge the gap between expert-level services and financial limits for cost-conscious homeowners.
What the researchers tested
The researchers built a predictive modelling framework using machine learning for personalized interior design recommendations. It combined content-based and collaborative filtering, used TF-IDF (Term Frequency–Inverse Document Frequency) and logistic regression, and was supported by primary data from small to medium-sized interior design companies. They also developed a web application tool and compared several models, including Random Forest, XGBoost, and KNN (K-Nearest Neighbors), using accuracy, precision, recall, and ROC-AUC (Receiver Operating Characteristic-Area Under the Curve).
What worked and what didn't
The logistic regression hybrid model achieved the best overall performance, with an accuracy of 83.62%. The abstract says the proposed approach outperformed the other tested models overall, but it does not provide the full metric values for the other models.
What to keep in mind
The summary does not describe detailed limitations, and it does not report how the system performed outside the tested setting. The abstract also does not give full comparative results for every model or enough detail to judge performance across all use cases.
Key points
- A hybrid interior design recommendation system was proposed using machine learning.
- The best-performing model was logistic regression, with 83.62% accuracy.
- The system combined content-based and collaborative filtering with TF-IDF and logistic regression.
- Primary data came from small to medium-sized interior design companies.
- The authors say the work may improve personalization and accessibility for cost-conscious homeowners.
Disclosure
- Research title:
- Hybrid recommendation model improved interior design service matching
- Authors:
- Pranabanti Karmaakar, Muhammad Aslam Jarwar, Junaid Abdul Wahid, Najam Ul Hasan
- Institutions:
- Sheffield Hallam University, Sheffield Hallam University, Sheffield Hallam University, Zhengzhou University
- Publication date:
- 2026-04-07
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with peer-reviewed research without reading academic papers — one filtered digest, every Friday.