Research on Cold Start Problem Mitigation Strategies 
for Big Data Recommender Systems Based on Deep 
Collaborative Filtering (DCF)

Xiaoxi Liu; Shuhao Dong

doi:10.70711/aitr.v2i11.7410

Research on Cold Start Problem Mitigation Strategies for Big Data Recommender Systems Based on Deep Collaborative Filtering (DCF)

Xiaoxi Liu, Shuhao Dong

Abstract

This paper focuses on the cold-start problem in big data recommendation system and proposes a mitigation strategy based on Deep
Collaborative Filtering (DCF) technology. The study first analyses the definition, causes and existing solutions of the cold-start problem, and
points out the shortcomings of traditional methods in dealing with cold-start data. The basic principles of DCF technology and its application status in recommender systems are introduced, and its feasibility in coping with the cold-start problem is explored. On this basis, a DCF
model fusing feature and embedding representation is designed, and its effectiveness in cold-start scenarios is verified through experiments.
The results show that the method outperforms traditional methods in terms of recommendation accuracy and stability. The study provides a
new idea to improve the performance of recommender system, which has practical application value.

Keywords

Deep collaborative filtering; Recommender system; Cold start problem; Feature fusion

Full Text:

PDF

Included Database

References

[1] Wei J, He J, Chen K, et al. Collaborative Filtering and Deep Learning Based Recommendation System For Cold Start Items[J]. Expert

Systems with Applications, 2016, 69:29-39.

[2] A S N, A S V, A S N, et al. Resolving data sparsity and cold start problem in collaborative filtering recommender system using Linked

Open Data-Science Direct[J]. Expert Systems with Applications, 149[2025-06-30].

[3] Mishra K N, Mishra A, Barwal P N, et al. Natural Language Processing and Machine Learning-Based Solution of Cold Start Problem

Using Collaborative Filtering Approach[J]. ELECTRONICS, 2024, 13(21):4331.

[4] Panda D K, Ray S. Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature

review[J]. Journal of Intelligent Information Systems, 2022, 59(2):341-366.

[5] Shetty A M, Manjaiah D H, Aljunid M F, et al. Comparative Analysis of Memory-Based Collaborative Filtering and Deep Learning

Models for Resolving Cold Start and Data Sparsity Issues in E-commerce Recommender Systems[C]//2024 IEEE 3rd World Conference

on Applied Intelligence and Computing (AIC).0[ 2025-06-30].

DOI: http://dx.doi.org/10.70711/aitr.v2i11.7410

Refbacks

There are currently no refbacks.