• 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) K-means Ŭ·¯½ºÅ͸µÀ» »ç¿ëÇÑ SVD ±â¹ÝÀÇ ±³Â÷ µµ¸ÞÀÎ Ãßõ
¿µ¹®Á¦¸ñ(English Title) SVD-based Cross-Domain Recommendation Using K-means Clustering
ÀúÀÚ(Author) ±èÅÂÈÆ   ±è¼º±Ç   Tae-Hoon Kim   Sung Kwon Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 49 NO. 05 PP. 0360 ~ 0368 (2022. 05)
Çѱ۳»¿ë
(Korean Abstract)
±³Â÷ µµ¸ÞÀÎ ÃßõÀº ´Ù¸¥ µµ¸ÞÀο¡ ÀÖ´Â °ü·Ã »ç¿ëÀÚ Á¤º¸ µ¥ÀÌÅÍ¿Í ¾ÆÀÌÅÛ µ¥ÀÌÅÍ °øÀ¯¸¦ ÅëÇØ ÇØ°áÇÏ°íÀÚ ÇÏ´Â ¹æ¹ýÀÌ´Ù. »ç¿ëÀÚ Áߺ¹ÀÌ ¸¹Àº ¿Â¶óÀÎ ¼îÇθôÀ̳ª À¯Æ©ºê(YouTube) ¶Ç´Â ³ÝÇø¯½º(NetFlix)¿Í °°ÀÌ ¸ÖƼ¹Ìµð¾î ¼­ºñ½º ÄÁÅÙÃ÷¿¡¼­ ÁÖ·Î »ç¿ëµÈ´Ù. K-means Ŭ·¯½ºÅ͸µÀ» ÅëÇØ »ç¿ëÀÚ µ¥ÀÌÅÍ¿Í ÆòÁ¡À» ±â¹ÝÀ¸·Î ±ºÁýÈ­¸¦ ½Ç½ÃÇÏ¿© ÀÓº£µùÀ» »ý¼ºÇÑ´Ù. ±× °á°ú¸¦ ´ÙÃþ ½Å°æ¸Á(Multi Layer Neural Network)¸¦ ÅëÇØ ÇнÀ½ÃŲ ÈÄ, »ç¿ëÀÚ ¸¸Á·µµ¸¦ ¿¹ÃøÇÑ´Ù. ±× ÈÄ Çù¾÷ ÇÊÅ͸µ ±â¹ýÀÎ Çà·Ä ºÐÇØ(matrix factorization)¸¦ ÀÌ¿ëÇÏ¿© »ç¿ëÀÚ¿¡°Ô ¸Â´Â ¾ÆÀÌÅÛµéÀ» ÃßõÇÑ´Ù. ÀÌ ¿¬±¸¸¦ ÅëÇØ ÃßõÇÔÀ¸·Î½á ´õ ÀûÀº ½Ã°£Àû ºñ¿ëÀ¸·Î Ãʱ⠻ç¿ëÀÚ ¹®Á¦¿¡ ´ëÇØ ¿¹ÃøÀÌ °¡´ÉÇÏ°í, »ç¿ëÀÚµéÀÇ ¸¸Á·µµ¸¦ ³ôÀÏ ¼ö ÀÖ´Ù´Â °á°ú¸¦ ½ÇÇèÀ» ÅëÇØ º¸¿©ÁÖ¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
Cross-domain recommendation is a method that shares related user information data and item data in different domains. It is mainly used in online shopping malls with many users or multimedia service contents, such as YouTube or Netflix. Through K-means Clustering, embeddings are created by performing clustering based on user data and ratings. After learning the result through a multi-layer neural network, user satisfaction is predicted. Then, items suitable for the user are recommended using matrix factorization, which is a collaborative filtering technique. Through this study, it was shown through experiments that recommendations can predict cold-start problems at a lesser time cost and increase the user satisfaction.
Å°¿öµå(Keyword) ±³Â÷ µµ¸ÞÀÎ Ãßõ   µ¥ÀÌÅÍ °øÀ¯   Çù¾÷ ÇÊÅ͸µ   K-means Ŭ·¯½ºÅ͸µ   Çà·Ä ºÐÇØ   ´ÙÃþ ½Å°æ¸Á   cross-domain recommendation   data sharing   collaborative filtering   matrix factorization   K-means clustering   multi-layer neural networks  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå