• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.529-536
• /
• 2023

The secondhand market in Korea has been showing steady growth. However, the number of fraud cases and the amount of damages from fraudulent activities in secondhand transactions are also increasing. As of 2021, the size of the secondhand market reached 24 trillion won, but the total amount of fraud-related damages reached 360.6 billion won. In order to prevent fraud between individuals, secondhand trading platforms have implemented a safety payment system. However, new types of fraud methods exploiting the safety payment system have emerged, undermining the security of secondhand transaction safety payments. In this study, we aim to utilize text mining to examine the current state of the safety payment system in secondhand transactions and propose improvement measures by analyzing the system through text mining and network analysis.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.469-471
• /
• 2023

본 논문에서는 기존 중고거래 플랫폼들의 불편한 점들을 해소하고 사용자들이 효율적이고 편리한 중고거래를 할 수 있도록 도와주는 플랫폼을 개발했다. 조사를 통해 기존 중고거래 플랫폼은 허위 매물, 시세 파악의 어려움, 사기 피해 등의 문제점이 존재한다는 사실을 인식했다. 문제 해결을 위해 파이썬을 활용하여 주요 중고거래 플랫폼의 상품 데이터를 수집했다. 이에 IQR을 적용하여 가격의 이상치를 판별했다. 가격 비교와 허위 매물 판별이 용이하게 되는 장점이 있다. 또한 이상치를 제거한 상품들의 시세를 계산하여 데이터를 차트로 시각화했다. 플랫폼과 지역마다 상이한 중고 상품의 신뢰성 있는 시세를 파악할 수 있고 중고거래 사기 피해를 방지할 수 있도록 사용자에게 주요 사기 수법, 뉴스 등의 정보를 제공한다.

• Information Systems Review
• /
• v.23 no.4
• /
• pp.45-67
• /
• 2021

As the transaction volume of the C2C second-hand market is growing, the number of frauds, which intend to earn unfair gains by sending products different from specified ones or not sending them to buyers, is also increasing. This study explores the model that can identify frauds in the online C2C second-hand market by examining the postings for transactions. For this goal, this study collected 145,536 field data from actual C2C second-hand market. Then, the model is built with the characteristics from postings such as the topic and the linguistic characteristics of the product description, and the characteristics of products, postings, sellers, and transactions. The constructed model is then trained by the machine learning algorithm XGBoost. The final analysis results show that fraudulent postings have less information, which is also less specific, fewer nouns and images, a higher ratio of the number and white space, and a shorter length than genuine postings do. Also, while the genuine postings are focused on the product information for nouns, delivery information for verbs, and actions for adjectives, the fraudulent postings did not show those characteristics. This study shows that the various features can be extracted from postings written in C2C second-hand transactions and be used to construct an effective model for frauds. The proposed model can be also considered and applied for the other C2C platforms. Overall, the model proposed in this study can be expected to have positive effects on suppressing and preventing fraudulent behavior in online C2C markets.

• Journal of Digital Convergence
• /
• v.16 no.9
• /
• pp.133-145
• /
• 2018

This study was investigated the necessity and possibility of using block-chain technology in online used-goods trading platform. Current online used-goods trading platforms operate a safety trading system, but it is difficult to utilize due to relatively high commission rate. As a result, people mainly use the method of meeting and purchasing in person, which is a relatively costly method. This study discusses how to build a platform to solve or mitigate problems such as privacy, information distortion and omission, fraud, etc. In the platform proposed in this study, it is possible to solve the major fraud and personal information protection problems that may occur in the transaction proceeding by appropriately reflecting the types and characteristics of the block-chain technology. In future work, we will discuss legal framework and technology development plan to apply the proposed platform in this study.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.191-194
• /
• 2020

본 연구에서는 안전하면서도 쉽게 사용할 수 있는 블록체인 기반의 중고 책 거래 플랫폼을 개발하였다. 이 플랫폼은 블록체인의 특성을 이용해 거래 제품 및 거래내역을 공유원장에 기록하여 거래내역을 투명하게 공개하며 누구나 열람 가능하다. 이는 데이터의 무결성과 투명성을 보장하며 신뢰성 있는 거래 환경을 제공한다. 이를 사용할 경우, 기존 중고거래 시스템에서 발생 가능한 데이터의 위조, 변조의 문제점과 불확실한 신뢰 문제가 해결되어 중고거래 사기사건을 예방할 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.173-182
• /
• 2022

In this paper, we propose a machine learning model that can prevent fraudulent transactions in advance and interpret them using the XAI approach. For the experiment, we collected a real data set of 12,258 mobile phone sales posts from Joonggonara, a major domestic online C2C resale trading platform. Characteristics of the text corresponding to the post body were extracted using Doc2vec, dimensionality was reduced through PCA, and various derived variables were created based on previous research. To mitigate the data imbalance problem in the preprocessing stage, a complex sampling method that combines oversampling and undersampling was applied. Then, various machine learning models were built to detect fraudulent postings. As a result of the analysis, LightGBM showed the best performance compared to other machine learning models. And as a result of SHAP, if the price is unreasonably low compared to the market price and if there is no indication of the transaction area, there was a high probability that it was a fraudulent post. Also, high price, no safe transaction, the more the courier transaction, and the higher the ratio of 0 in the price also led to fraud.

• Journal of Digital Convergence
• /
• v.18 no.4
• /
• pp.237-242
• /
• 2020

Online e-commerce management systems are gradually increasing, and transactions are made in various items. However, the reliability between sellers and buyers is very important in high-priced transactions such as automobiles when used transactions online. Nevertheless, in the existing used trading system, a device that prevents fraud or trusts the seller is insufficient. This paper developed a blockchain-based used transaction management system to improve the reliability that occurs during used transactions. We have improved the safety trading system by developing a trading management system for used cars with the highest amount of used cars in various fields. This system uses Ethereum-based smart contract to guarantee reliability without third party intervention. By designing the contracts required for used car trading by utilizing smart contracts, it was possible to reduce the effort and time of trading participants in the existing used car transactions, while enabling safe transactions. In addition, this system mitigated information asymmetry between buyers and sellers, and reduced and prevented brokerage fees in the distribution process without third parties.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.482-485
• /
• 2014

온라인 중고물품 거래의 장점은 인터넷을 사용하는 모든 사용자에게 자신이 팔고자 하는 물건을 쉽게 알릴수 있다는것이다. 하지만 온라인에서 중고물품 거래 시에 개인의 정보를 노출할 경우가 많아지게 되는데 이는 프라이버시를 침해할 수 있다. 온라인 중고물품거래시에 사용자들은 자신이 판매하는 물건과 함께 이메일 주소나 핸드폰 번호를 노출하게 되는데 이 정보를 소셜네트워크서비스에 연결하면 특정인에 정보를 획득할 수 있게 된다. 공격자는 온라인 중고물품거래가 진행되는 곳에서 특정인에 대한 정보를 획득한뒤 소셜네트워크서비스와 정보를 연결하여 특정인에 대한 스토킹이나 피싱, 금융사기같은 범죄를 할 가능성이 있다. 본 논문에서는 개인정보노출에 대한 위험성을 알아보기 위해 중고물품 사이트에서 획득한 개인정보를 소셜네트워크서비스에 연결하여 개인 식별가능성을 실험해 보았으며 이를 막기 위한 방법을 제안하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.430-432
• /
• 2015

스마트폰의 보급과 소프트웨어 개발기술의 발전으로 다양한 어플리케이션이 출시되고 사용되어지고 있다. 특히, 스마프폰을 통해 모바일 쇼핑뿐 아니라 개인간 거래가 활성화되고 있다. 하지만 사용자가 많아지면서 인터넷 사기 범죄도 증가하고 있는 추세이다. 사용자간의 교류가 많은 어플리케이션은 인증이 중요하다. 본 논문에서는 스마트폰 어플리케이션에서 활용하는 인증의 종류를 알아보고 모바일 중고 거래 어플리케이션의 사용자 인증의 종류와 신뢰도 측정방법을 비교 분석하고, 문제점을 파악하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.3 no.2
• /
• pp.37-42
• /
• 2017

An internet primary bank, which is formed by internet and banks combined, is called the essence of fin-tech, and is currently experiencing rapid growth. 'K-Bank' and 'Kakao Bank', the representative internet primary banks this year, received positive responses as the origin of financial revolution. internet primary banks provide convenient financial services, benefits in time and money for customers. Not long ago, however, undesirable fraud cases caused by a used commodity dealer have happened. The damage exceeds 20,000,000 won. It is because the newborn banks are unable to check the fraud history through the bank account. In this paper, We will analyze the trend in internet primary banks, offer damages and examples, in addition, prevention of damage, and strategies for development.