TY - GEN
T1 - Recent Developments in Recommender Systems
AU - Low, Jia-Ming
AU - Tan, Ian K. T.
AU - Ting, Choo-Yee
N1 - Publisher Copyright:
© Springer Nature Switzerland AG 2019.
PY - 2019/10/21
Y1 - 2019/10/21
N2 - With greater penetration of online services, the use of recommender systems to predict users’ propensity for continuous engagement becomes crucial in ensuring maximum revenue. There are many challenges, such as the cold start problem and data sparsity, that are continuously being addressed by a myriad of techniques in recommender systems. This paper provides insights into the trends of the techniques used for recommender systems and the challenges they address. With the insights; deep learning, matrix factorization or a combination of both can be used in addressing the data sparsity challenge.
AB - With greater penetration of online services, the use of recommender systems to predict users’ propensity for continuous engagement becomes crucial in ensuring maximum revenue. There are many challenges, such as the cold start problem and data sparsity, that are continuously being addressed by a myriad of techniques in recommender systems. This paper provides insights into the trends of the techniques used for recommender systems and the challenges they address. With the insights; deep learning, matrix factorization or a combination of both can be used in addressing the data sparsity challenge.
UR - http://www.scopus.com/inward/record.url?scp=85076159417&partnerID=8YFLogxK
U2 - 10.1007/978-3-030-33709-4_4
DO - 10.1007/978-3-030-33709-4_4
M3 - Conference contribution
AN - SCOPUS:85076159417
SN - 9783030337087
T3 - Lecture Notes in Computer Science
SP - 38
EP - 51
BT - Multi-disciplinary Trends in Artificial Intelligence. MIWAI 2019
A2 - Chamchong, Rapeeporn
A2 - Wong, Kok Wai
PB - Springer
T2 - 13th Multi-disciplinary International Conference on Artificial Intelligence 2019
Y2 - 17 November 2019 through 19 November 2019
ER -