Each country/region has implemented some non-pharmaceutical interventions (NPIs),such as school closure, workplace closure, restriction of gatherings, and stay-at-home requirement,to control COVID-19 epidemic. It is important to analyze the association between the NPIsand COVID-19 incidence and to estimate the impact of each of the NPIs against COVID-19 forthe future policy-making. Although the impact potentially differs depending on country/regionfeatures (e.g. society, economy, life style), existing works for analysis of COVID-19 transmissiongrowth and control according to NPIs and country/region features are done separately, and noanalysis of the impact of each NPIs with respect to country/region features has been done asof yet. In this paper, we extract exhaustively combination of NPIs and country/region featuresassociated with COVID-19 incidence using "Wide Learning" developed by Fujitsu Laboratories,and propose hypotheses for impact of the NPIs against COVID-19 with respect to country/regionfeatures as well as comparing our findings with findings on the existing analysis of the impact ofNPIs against COVID-19.

In Europe and the United States, appearance is considered to be an important factor in business,and not a few studies have examined the effects of managerial appearance on corporate management andindividual success and performance. In this study, we attempt to analyze quantitatively the faces ofmanagers in Japan, which is one of the most important components of appearance, in order to elucidatewhether a similar phenomenon is found in Japan. Photographs of managers' faces are collected fromannual reports and other sources, and feature vectors are extracted. This will be clustered using theK-means method using FaceNet's trained model VGGFace2 to analyze whether there are differences inthe behavior of the companies in each cluster, i.e., how the face of the manager affects the company'sbehavior.

Stock market fluctuations are caused by various factors. This study focuses on news articles toimprove the accuracy of stock market predictions. The effect of news articles is bigger when informationthat was not predicted is public, earning surprise. We have summarized past news articles by GPT-2 todiscover news trends. We also converted the news articles into vectors and link them to stock prices bymachine learning. As a result of this analysis, we were able to improve the accuracy of stock market pre-dictions.

Labor shortage due to population decline is a social issue in Japan.On the other hand, in April 2019, the "Work Style Reform Laws" was enacted, and diversification of workstyles and improvement of productivity can be seen as a management issue for Japanese companies.In this paper, we propose a method to detect various work situations and meeting occurrences of employees,in order to find out the relationship of interaction between "work style" and "productivity", using locationinformation data obtained from in-house Wi-Fi connection. In addition, by analyzing the network basedon the information of the detected meeting, the network in the organization can be visualized.In this way, we aim to identify a model that maximizes organizational productivity by visualizing the wayemployees work styles.

Gas and electric power are one of the essential social infrastructure for social and economicactivities. The purpose of this research is to construct a Real Time Pricing (RTP) model suitable for thedistribution and sales market of LP gas in Japan by utilizing the Dynamic Pricing Model. As a method ofpredicting demand, we would like to first create a model of power consumption and then apply it to LPgas. Analysis of customers' electric power and gas consumption can infer from what standpoint they wereconsuming public goods. Through this, we would like to offer users' reasonable prices to expand theirchoices and contribute to the efficient use of social resources.

With the aging of society, the problem of asset formation before and after retirement isattracting attention. The issues related to asset depletion are often analyzed based on macro statistical datasuch as financial assets and disposable income. Whereas such analysis does not necessarily reflect theattributes of each individual so there is room for improvement. In this paper, as a first step to analyze thecharacteristics of the assets and household income before and after retirement, we conducted a basicanalysis using individual questionnaire data. Specifically, after showing the summary statistics of theabove data, cross tabulation was performed according to the attributes of the questionnaire respondents.We analyzed the tendency of various asset statuses and stances toward investment due to differences inresidential area and household composition.

This study proposes a method of using Data Envelopment Analysis (DEA) to classify a set ofinput/output logs in a social or organizational simulation and compares it with previous methods based oncluster analysis using examples. DEA is used mainly in policy analysis as a method to compare theefficiency based on multiple input and multiple output data. In DEA, the entire data is partitioned by thedata that define efficiency corner points, called reference sets. In this study, we propose to use DEA as aclassifier of simulation logs due to this property of reference sets. In this paper, we illustrate how DEAallows us to classify a set of simulation logs by their characteristics, using the SIR model of infectiousdisease spreading with additional variables multiple indicating measures. In addition, the results werecompared with the results of the previous log classification using cluster analysis.

In this research, we analyze the impact of crypto assets on portfolio construction. Through this research, weattempt to clarify the risk return characteristics of portfolios that include crypto assets as investment targets. Theanalysis period is from 2014 to 2020, and in addition to the Cryptocurrency Index (CRIX), S&P500, Gold, Crude oil,PE, REITs, Goldman Sachs Commodity Index (GSCI), etc. Consider effectiveness and challenges.