• 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¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ¿Â¶óÀÎ °ÔÀÓ ³» À¯Àú °£ »óÈ£ÀÛ¿ë ºÐ¼®À» ÅëÇÑ À¯Àú ÀÌÅ» ¿¹Ãø
¿µ¹®Á¦¸ñ(English Title) Churn Prediction in Online Games through User Interaction Analysis
ÀúÀÚ(Author) ¹®ÁÖ¿¬   ±èÈÖ°­   ¿ìÁö¿µ   Joo Yeon Moon   Huy Kang Kim   Jiyoung Woo  
¿ø¹®¼ö·Ïó(Citation) VOL 24 NO. 09 PP. 0443 ~ 0441 (2018. 09)
Çѱ۳»¿ë
(Korean Abstract)
º» ¿¬±¸¿¡¼­´Â ´ë±Ô¸ð ´ÙÁß »ç¿ëÀÚ ¿Â¶óÀÎ ·ÑÇ÷¹À× °ÔÀÓ(MMORPG) ³»¿¡¼­ ÀϾ´Â ¼Ò¼ÈÈ°µ¿ÀÌ À¯Àú ÀÌÅ»¿¡ ¹ÌÄ¡´Â ¿µÇâ¿¡ ´ëÇØ ºÐ¼®ÇÏ¿´´Ù. MMORPG ³»¿¡¼­´Â À¯Àú °£ »óÈ£ÀÛ¿ëÀÌ Áß¿äÇÑ ¿ªÇÒÀ» ÇÏ´Â °æ¿ì°¡ ¸¹°í, µû¶ó¼­ À̸¦ Á¦°øÇÏ´Â Ä¿¹Â´ÏƼ ½Ã½ºÅÛÀÌ ¹ß´ÞÇÏ¿´´Ù. ´ëÇ¥ÀûÀ¸·Î ¡°Äù½ºÆ®¡± µîÀÇ ¹Ì¼Ç Çù¾÷À» À§ÇÑ ÆÄƼ¿Í ±×º¸´Ù Áö¼ÓÀûÀÎ ¼Ò¼È È°µ¿À» Á¦°øÇÏ´Â ±æµå µîÀÌ ±×¿¡ ¼ÓÇÑ´Ù. º» ¿¬±¸´Â MMORPGÀÇ ½ÇÁ¦ µ¥ÀÌÅ͸¦ ÀÌ¿ëÇÏ¿© ÀÏÁ¤ ±â°£ ³»¿¡ ÀÌÅ»ÇÑ À¯Àú¿Í Áö¼ÓÀûÀ¸·Î °ÔÀÓÀ» ÀÌ¿ëÇÑ À¯Àú¸¦ ÃßÃâÇÏ°í, µÎ À¯ÀúÀÇ ÀÌÅ» Á÷Àü È°µ¿ ·Î±×¸¦ ¼Ò¼È ÇàÀ§¸¦ Áß½ÉÀ¸·Î ºÐ¼®ÇÏ¿© ÀÌÅ»ÇÑ À¯Àú¿¡°Ô¼­ ³ªÅ¸³ª´Â Ư¼ºÀ» ÃßÃâÇÏ¿´´Ù. ÀÌÈÄ ÃßÃâÇÑ Æ¯¼ºÀ» ±â¹ÝÀ¸·Î ÇÏ¿© È°µ¿ ·Î±×¸¦ Á¤Á¦ÇØ ÇÇÃĸ¦ Á¤ÀÇÇÏ°í, À¯Àú ÀÌÅ»¿¹Ãø ¸ðµ¨À» Á¦½ÃÇÏ¿´´Ù. º» ³í¹®¿¡¼­´Â °üÂûÇÒ È°µ¿ ·Î±× ¼ö¿Í ºÐ·ù ¸ðµ¨ ÇнÀ¿¡ »ç¿ëµÇ´Â ÇÇÃÄÀÇ °³¼ö¸¦ ÁÙ¿© ºü¸£°Ô À¯Àú ÀÌÅ»À» ¿¹ÃøÇÒ ¼ö ÀÖ´Â ¹æ¹ýÀ» Á¦½ÃÇÏ¿´´Ù.
¿µ¹®³»¿ë
(English Abstract)
This study analyzes the effect of social activities in massive multi-user online role-playing games (MMORPG) on user churn. In MMORPG, interactions between users often play an important role, and community systems that provide users¡¯ social behaviors have developed. Typically, there are parties for mission collaboration, such as "Quest," and guilds that provide more and longer social activities. In this study, we obtained the actual data from a major MMORPG. Using this data, we extract users who stop playing the game within a certain period of time, namely. churn users, and analyze their characteristics. Then we extract features from the extracted characteristics of churn users to present a user churn prediction model. In this paper, we propose a lightweight and quick prediction model by reducing the number of action logs to be observed and the number of features used in the classification model.
Å°¿öµå(Keyword) ¿Â¶óÀÎ °ÔÀÓ   À¯Àú »óÈ£ÀÛ¿ë   À¯Àú ÀÌÅ» ¿¹Ãø   online game   user interaction   user churn prediction  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå