Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Spark¸¦ ÀÌ¿ëÇÑ Ç׸ñ Ãßõ ±â¹ý¿¡ °üÇÑ ¿¬±¸ |
¿µ¹®Á¦¸ñ(English Title) |
Item Recommendation Technique Using Spark |
ÀúÀÚ(Author) |
À¯ÀºÀç
Á¤ÈÖ»ó
ÀÌÇö¼·
±èÁø´ö
Eun-Jae You
Hwi-Sang Jeong
Hyoun-Sup Lee
Jin-deog Kim
À±¼Ò¿µ
À±¼º´ë
So-Young Yun
Sung-Dae Youn
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 22 NO. 05 PP. 0715 ~ 0721 (2018. 05) |
Çѱ۳»¿ë (Korean Abstract) |
¸ð¹ÙÀÏ ±â±âÀÇ È®»êÀ¸·Î ¼Ò¼È ³×Æ®¿öÅ© ¼ºñ½º³ª ÀüÀÚ»ó°Å·¡ »çÀÌÆ®ÀÇ »ç¿ëÀÚ ¼ö°¡ ±ÞÁõÇÏ°í ÀÖ°í »ç¿ëÀÚµéÀÌ ³²±ä µ¥ÀÌÅÍÀÇ ¾çµµ ±âÇϱ޼öÀûÀ¸·Î Áõ°¡ÇÏ°í ÀÖ´Ù. ±×·Î ÀÎÇØ ÀüÀÚ »ó°Å·¡ ±â¾÷µéÀº »ç¿ëÀÚµéÀÌ ³²±ä ¹æ´ëÇÑ ¾çÀÇ µ¥ÀÌÅͷκÎÅÍ ¾î¶»°Ô À¯¿ëÇÑ Á¤º¸¸¦ ÃßÃâÇÒ °ÍÀΰ¡ ÇÏ´Â °úÁ¦¸¦ °®°Ô µÇ¾ú´Ù. ÀÌ·¯ÇÑ ¹®Á¦¸¦ ÇØ°áÇϱâ À§ÇØ Ãßõ ½Ã½ºÅÛ¿¡ ºò µ¥ÀÌÅÍ Ã³¸® ±â¹ýÀ» Àû¿ëÇÑ ´Ù¾çÇÑ ¿¬±¸µéÀÌ ÀÌ·ç¾îÁö°í ÀÖ´Ù. º» ³í¹®¿¡¼´Â Apache Spark Ç÷§Æû¿¡¼ Tag °¡ÁßÄ¡¸¦ Àû¿ëÇÑ Çù¾÷ ÇÊÅ͸µ ±â¹ýÀ» »ç¿ëÇÑ Ãßõ¹æ½ÄÀ» Á¦¾ÈÇÑ´Ù. Á¦¾ÈÇÏ´Â ±â¹ýÀº ÃßõÀÇ Á¤È®¼ºÀ» ³ôÀ̱â À§ÇØ Àüó¸® °úÁ¤¿¡¼ Tag µ¥ÀÌÅ͸¦ Á¤Á¦ÇÏ°í ¾ÆÀÌÅÛÀ» ºÐ·ùÇÑ ÈÄ ¾ÆÀÌÅÛ Æò°¡°ª¿¡ ±â°£ Á¤º¸¿Í Tag °¡ÁßÄ¡¸¦ Àû¿ëÇÏ¿© »ç¿ëÇÑ´Ù. RDD(Resilient Distributed Dataset)¸¦ »ý¼ºÇÑ ÈÄ ¾ÆÀÌÅÛ À¯»çµµ¿Í ¿¹Ãø°ªÀ» ±¸ÇÏ°í »ç¿ëÀÚ¿¡°Ô ¾ÆÀÌÅÛÀ» ÃßõÇÑ´Ù. ½ÇÇèÀ» ÅëÇØ Á¦¾È ÇÏ´Â ±â¹ýÀÌ ´ë·®ÀÇ µ¥ÀÌÅ͸¦ ºü¸£°Ô ó¸®ÇÏ°í ÃßõÀÇ ÀûÇÕ¼ºµµ Çâ»óµÇ´Â °ÍÀ» È®ÀÎÇÏ¿´´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
With the spread of mobile devices, the users of social network services or e-commerce sites have increased dramatically, and the amount of data produced by the users has increased exponentially. E-commerce companies have faced a task regarding how to extract useful information from a vast amount of data produced by the users. To solve this problem, there are various studies applying big data processing technique. In this paper, we propose a collaborative filtering method that applies the tag weight in the Apache Spark platform. In order to elevate the accuracy of recommendation, the proposed method refines the tag data in the preprocessing process and categorizes the items and then applies the information of periods and tag weight to the estimate rating of the items. After generating RDD, we calculate item similarity and prediction values and recommend items to users. The experiment result indicated that the proposed method process large amounts of data quickly and improve the appropriateness of recommendation better.
|
Å°¿öµå(Keyword) |
°¡»óÇö½Ç
°ü¼º ÃøÁ¤ ÀåÄ¡
±ÙÁ¢¼¾¼
µ¿±âÈ
À̵¿°´Ã¼
Visual Reality
IMU(Inertial Measurement Unit)
Proximity Sensor
Synchronization
Moving Object
Ãßõ±â¹ý
Çù¾÷ÇÊÅ͸µ
¾ÆÆÄÄ¡ ½ºÆÄÅ©
È®À强
ű×
Recommendation Technique
Collaborative Filtering
Apache Spark
Scalability
Tag
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|