• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Á¤º¸°úÇÐȸ³í¹®Áö (Journal of KIISE)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ÄÝµå ½ºÅ¸Æ® ¹®Á¦ ¿ÏÈ­¸¦ À§ÇÑ °¡ÁßÄ¡ ±â¹Ý ´ÙÁß µµ¸ÞÀÎ Ãßõ ½Ã½ºÅÛ
¿µ¹®Á¦¸ñ(English Title) A Weight-based Multi-domain Recommendation System for Alleviating the Cold-Start Problem
ÀúÀÚ(Author) ¹®¼±¾Æ   °í»ó±â   Seona Moon   Sang-Ki Ko  
¿ø¹®¼ö·Ïó(Citation) VOL 48 NO. 10 PP. 1090 ~ 1096 (2021. 10)
Çѱ۳»¿ë
(Korean Abstract)
Ãßõ ½Ã½ºÅÛÀº »ç¿ëÀÚÀÇ ±â·Ï°ú Ç׸ñ ¼±È£µµ¸¦ ±â¹ÝÀ¸·Î ÇØ´ç »ç¿ëÀÚ°¡ ¼±È£ÇÒ °ÍÀ¸·Î ¿¹ÃøµÇ´Â Ç׸ñÀ» ÃßõÇÑ´Ù. Ãßõ ½Ã½ºÅÛ¿¡´Â ±âÁ¸ »ç¿ëÀÚÀÇ Á¤º¸¸¦ ±â¹ÝÀ¸·Î ºñ½ÁÇÑ ¼ºÇâÀÇ »ç¿ëÀÚ ÆòÁ¡À» ¿¹ÃøÇÏ´Â Çù¾÷ ÇÊÅ͸µ ¹æ½ÄÀÌ ÀÖ´Ù. »ç¿ëÀÚÀÇ ¼ºÇâÀ» ¾Ë±â À§ÇØ ±¸¸Å À̷°ú °°Àº Á¤º¸°¡ ÇÊ¿äÇѵ¥ ÀÌ Á¤º¸°¡ ¾øÀ» ¶§ ¿¹ÃøÀÌ ¾î·Á¿öÁö´Âµ¥ À̸¦ ÄÝµå ½ºÅ¸Æ® ¹®Á¦(cold-start problem)¶ó ÇÑ´Ù. º» ³í¹®¿¡¼­´Â ƯÁ¤ µµ¸ÞÀο¡ ¾Æ¹« Á¤º¸°¡ ¾ø´Â Ãʱ⠻ç¿ëÀÚ¸¦ À§ÇØ »ç¿ëÀÚ°¡ ´Ù¸¥ µµ¸ÞÀο¡ ³²±ä ÆòÁ¡ Á¤º¸¸¦ ±â¹ÝÀ¸·Î »õ·Î¿î µµ¸ÞÀÎÀÇ ÆòÁ¡ Á¤º¸¸¦ ¿¹ÃøÇÏ´Â ´ÙÁß µµ¸ÞÀÎ Ãßõ ½Ã½ºÅÛÀ» Á¦¾ÈÇÑ´Ù. À̶§, ¿©·¯ º¸Á¶ µµ¸ÞÀÎÀ¸·Î ¿¹ÃøÇÑ ÆòÁ¡ Á¤º¸ÀÇ ½Å·Úµµ¸¦ ±Ø´ëÈ­Çϱâ À§ÇØ °¢ º¸Á¶ µµ¸ÞÀÎÀÇ °¡ÁßÄ¡¸¦ °è»êÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÏ°í ½ÇÇèÀ» ÅëÇØ ¼º´ÉÀ» °ËÁõÇÑ´Ù. ±× °á°ú, ÀüÅëÀûÀÎ Ãßõ ¾Ë°í¸®ÁòÀ» ´ÙÁß µµ¸ÞÀο¡ ´Ü¼ø Àû¿ëÇßÀ» ¶§º¸´Ù °¡ÁßÄ¡ ±â¹Ý Ãßõ ¾Ë°í¸®ÁòÀ» È°¿ëÇßÀ» ¶§ ´õ ³ªÀº Ãßõ ¼º´ÉÀ» º¸ÀÌ´Â °ÍÀ» È®ÀÎÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
A recommendation system predicts users¡¯ ratings based on users¡¯ past behaviors and item preferences. One of the most famous types of recommendation systems is the collaborative filtering method that predicts users¡¯ ratings based on the rating information from users with similar preferences. In order to predict the preferences of users, we need adequate information about users¡¯ interactive information on items. Otherwise, it is very difficult to make accurate predictions for users without adequate information. This phenomenon is called the cold-start problem. In this paper, we propose a multi-domain recommendation system that utilizes the rating information of multiple domains. We propose a method that calculates the weight of each auxiliary domain to maximize the confidence of predicted ratings from multiple auxiliary domains and verify the performance of the proposed method through extensive experiments. As a result, we demonstrate that our algorithm produces better recommendation results compared to the classical algorithms simply utilized in multiple domain settings.
Å°¿öµå(Keyword) Ãßõ ½Ã½ºÅÛ   Çù¾÷ ÇÊÅ͸µ   ÄÝµå ½ºÅ¸Æ® ¹®Á¦   ´ÙÁß µµ¸ÞÀÎ Ãßõ   recommendation system   collaborative filtering   cold-start problem   multi-domain recommendation  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå