摘要：In March 2021, a case of speculation that abused private internal information came to light, which involved a group of public officials from the Korea Land and Housing Corporation (LH), and has since been labeled the ‘LH Scandal’. In this scandal, land was misappropriated as a means of creating fraudulent values, instead of returning it to marginalized people in real need of residential space. As a result of this, preventive measures for similar cases have become warranted. Consequently, related laws have been passed, but this is only expected to show its effect as a follow-up response, therefore requiring a preemptive response plan. In this paper, we will propose a conceptual framework that can detect speculation that abuses private internal information, enabling a preemptive response, utilizing outlier detection and Latent Dirichlet Allocation (LDA) methods. The system is designed to create a database (DB) with private inside real estate information, which is linked to another DB with a list of outlier-detected areas that can potentially indicate speculation, and then the system confirms any speculation by comparing the two DBs accordingly. Once a speculation case is confirmed, the system automatically reports the case to the investigative agency. By using this system, we expect to detect hidden speculation cases already committed, as well as speculation cases in real-time. Ultimately, we hope to protect the original purpose of redevelopment and the construction of new towns (housing/retail mixed-use zones), redistributing available land on behalf of marginalized people, who are lacking in residential space, by raising the utility of land.
