• 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 : 41 / 42

ÇѱÛÁ¦¸ñ(Korean Title) ¿ÀÅäÀÎÄÚ´õ¸¦ È°¿ëÇÑ È¿À²ÀûÀÎ ½Å¿ëÄ«µå »ç±â ŽÁö Áöµµ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Efficient Supervised Credit Card Fraud Detection Technique using Autoencoder
ÀúÀÚ(Author) ÀÌ¿ëÇö   ±¸Çظ𠠠±èÇüÁÖ   YongHyun Lee   HeyMo Kou   Hyoung-Joo Kim  
¿ø¹®¼ö·Ïó(Citation) VOL 25 NO. 01 PP. 0001 ~ 0008 (2019. 01)
Çѱ۳»¿ë
(Korean Abstract)
½Å¿ëÄ«µå °áÁ¦ ÀÌ»ó °Å·¡ ŽÁö´Â Ä«µåÀÇ »ç¿ëÀÌ ½Ç½Ã°£À¸·Î ÀÌ·ç¾îÁö°í, ŽÁö°¡ Áï°¢ÀûÀ¸·Î ÀÌ ·ç¾îÁ®¾ß ÇÑ´Ù´Â Á¡¿¡¼­ ½ºÆ®¸®¹Ö µ¥ÀÌÅÍ ºÐ¼®À¸·Î º¼ ¼ö ÀÖ°í, ÀÌ´Â ¹èÄ¡ ºÐ¼®º¸´Ù ´õ ºü¸¥ ½Ç½Ã°£ ºÐ¼® À» ¿ä±¸ÇÑ´Ù. µ¥ÀÌÅÍ¿¡¼­ ÇÙ½É ºÎºÐ¸¸À» ÃßÃâÇÏ¿© ºÐ¼®ÇÏ´Â ¹æ¹ýÀº ÀÌ·¯ÇÑ ¿¬»ê ¼ÓµµÀÇ ¿ä±¸»çÇ×À» Àß ¸¸ Á·½Ãų ¼ö ÀÖÀ» °ÍÀÌ°í, ÁÖ¼ººÐ ºÐ¼® µîÀÇ ±â¹ýÀ» ÅëÇØ ÀÌ·ç¾îÁ® ¿Ô´Ù. º» ³í¹®¿¡¼­´Â Àΰø½Å°æ¸ÁÀ» È°¿ë ÇÑ Â÷¿ø Ãà¼Ò ±â¹ýÀÎ ¿ÀÅäÀÎÄÚ´õ·Î µ¥ÀÌÅ͸¦ Àüó¸®ÇÏ¿© µ¥ÀÌÅÍÀÇ Â÷¿øÀ» Ãà¼ÒÇÑ ÈÄ µ¥ÀÌÅÍ ¸¶ÀÌ´× ±â¹ý À» Àû¿ëÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ¿ÀÅäÀÎÄÚ´õ´Â µ¥ÀÌÅÍ Â÷¿øµé °£ÀÇ ºñ¼±ÇüÀûÀÎ °áÇÕ °ü°èµµ Æ÷ÂøÇÒ ¼ö Àֱ⠿¡ º¸´Ù È¿°úÀûÀÎ Â÷¿ø Ãà¼Ò ¹æ¹ýÀÌ´Ù. ¶ÇÇÑ À̸¦ µ¥ÀÌÅͺ£À̽º ³»¿¡¼­ÀÇ ÀÌ»ó ŽÁö ºÐ¼®¿¡ ¾î¶»°Ô »ç¿ë ÇÒ Áö¿¡ ´ëÇÏ¿© CQL°úÀÇ ¿¬µ¿ ¹æ¹ý·ÐÀ» Á¦½ÃÇÏ°íÀÚ ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
Credit card fraud detection can be viewed as Streaming Data Analysis in which a card is used in real time and the detection must be done immediately. This requires a real time analysis that is faster than the batch analysis. The method of extracting and analyzing only the core part of the data will satisfy the requirements of this computation speed. This has been done through techniques such as principal component analysis. In this paper, we propose a method that applies data mining techniques after reducing the dimension of data by preprocessing the data with Autoencoder. This method is known as the dimension reduction method and it uses a Neural Network. Autoencoder is a very efficient method of dimension reduction because it can capture nonlinear associations between data feature dimensions. We also propose a methodology to combine Autoencoder with CQL for fraud detection analysis in the database.
Å°¿öµå(Keyword) ¿ÀÅäÀÎÄÚ´õ   ÀÌ»ó °Å·¡ ŽÁö   Â÷¿ø Ãà¼Ò   µ¥ÀÌÅÍ Á¤¸®   autoencoder   fraud detection   dimentionality reduction   data reduction  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå