Hyungseok Kim

A deep learning-based sports player evaluation model based on game statistics and news articles

Player evaluation is a key component of the question-answering (QA) system in sports. Since existing player evaluation methods heavily rely on game statistics, they cannot capture the qualitative impact of each player during a game, which can be exploited using news articles after the game. In this paper, we propose a deep learning-based player evaluation model by combining both quantitative game statistics and the qualitative analyses provided by news articles. Players are classified as positive or negative based on their performance during certain periods, and news articles in the same period are annotated using the players class. Then, the relationship between news articles and the annotated polarity is investigated by a deep neural network, which can deal with the high dimensionality of the text data. Since there is no explicit polarity label for news articles, we use the change in game statistics in target periods to annotate related sentences. The proposed system is applied to a Korean professional baseball league (KBO) and it is shown to be capable of understanding the sentence polarity of news articles on player performances.

Network Forensic Evidence Generation and Verification Scheme (NFEGVS)

One of the critical success factors of the cybercrime investigation is exact tracing back of hacker’s origin. However, criminals can easily modify or delete log files on victim machines. In addition, criminals can easily modify the source IP address so that network packet cannot be a strong evidence because it is easily spoofed. This study suggests a scheme for network forensic evidence generation and verification. This proposed scheme can show the attacker’s source location and guarantee the integrity of address fields. This scheme also can minimize the performance degradation of routers when generating forensic evidence via flow-based evidence traffic analysis.

Firewall ruleset visualization analysis tool based on segmentation

Although most companies operate a firewall to protect their information assets, they have difficulties in identifying the control conditions of firewalls. This study proposes an analysis tool to visualize segment-based firewall rules to facilitate verification of the current control conditions. The proposed visualization tool analyzes the current control conditions of packets automatically, thereby eliminating the need for manual inspection as before, and displays the conditions with a visualization model to allow them to be easily verified. This enables managers to perform fast and accurate verification to assess whether packets are allowed or denied. This present study involved implementing the proposed visualization tool, and simulations were conducted to verify that the proposed approach was achievable. The present study also included conducting interviews with firewall experts whose feedback was positive. A video of the proposed visualization tool can be found on the following web site: https://youtu.be/q4HMnBvXbk.

Evaluating Variable Selection Techniques for Multivariate Linear Regression

The purpose of variable selection techniques is to select a subset of relevant variables for a particular learning algorithm in order to improve the accuracy of prediction model and improve the efficiency of the model. We conduct an empirical analysis to evaluate and compare seven well-known variable selection techniques for multiple linear regression model, which is one of the most commonly used regression model in practice. The variable selection techniques we apply are forward selection, backward elimination, stepwise selection, genetic algorithm (GA), ridge regression, lasso (Least Absolute Shrinkage and Selection Operator) and elastic net. Based on the experiment with 49 regression data sets, it is found that GA resulted in the lowest error rates while lasso most significantly reduces the number of variables. In terms of computational efficiency, forward/backward elimination and lasso requires less time than the other techniques.

Death spiral issues in emerging market: A control related perspective

This paper studies the motive of issuing floating-priced convertibles or warrants, known as death spirals, in a country where private benefit of control is high. Using a total of 199 death spiral issuances by public firms listed in the Korea Stock Exchange during 1998–2006, we find a number of pieces of empirical evidence that are less consistent with the conventional last resort financing hypothesis, but rather consistent with the control enhancing or control transferring hypothesis. First, abnormal returns subsequent to death spiral issuance is negative, but more so in poorly governed firms. Second, operating performance of chaebol issuers are not necessarily low at the time of the issue nor does it deteriorate over time, but they still prefer to issue death spirals over traditional fixed-priced hybrid securities. Third, we do not observe subsequent changes in the controlling shareholder in more than 60% of the issuers and these firms exhibit superior operating performance at the time of the issue compared to other death spiral or non-death spiral issuers. Fourth, proportional ownership of the controlling party in these firms does not decrease, while the number of shares held by family members other than the controlling shareholder increases. Finally, in approximately half of these firms, at least one member of the controlling party holds hybrid securities that can later be converted into voting shares.

Death Spiral Issues in Emerging Market: A Control Related Perspective

This paper studies the motive of issuing floating-priced convertibles or warrants, known as death spirals, in a country where private benefit of control is high. Using a total of 199 death spiral issuances by public firms listed in the Korea Stock Exchange during 1998–2006, we find a number of pieces of empirical evidence that are less consistent with the conventional last resort financing hypothesis, but rather consistent with the control enhancing or control transferring hypothesis. First, abnormal returns subsequent to death spiral issuance is negative, but more so in poorly governed firms. Second, operating performance of chaebol issuers are not necessarily low at the time of the issue nor does it deteriorate over time, but they still prefer to issue death spirals over traditional fixed-priced hybrid securities. Third, we do not observe subsequent changes in the controlling shareholder in more than 60% of the issuers and these firms exhibit superior operating performance at the time of the issue compared to other death spiral or non-death spiral issuers. Fourth, proportional ownership of the controlling party in these firms does not decrease, while the number of shares held by family members other than the controlling shareholder increases. Finally, in approximately half of these firms, at least one member of the controlling party holds hybrid securities that can later be converted into voting shares.