CTM and QFD analysis: Framework for fintech adoption priority in commercial banks.

As financial technology (fintech) is developing rapidly, many commercial banks experience difficulty deciding what kind of fintech to primarily focus on when managing their business. Owing to limited resources and assets, there is a practical need for guidelines for banks' investments in fintech. This study provides a systemic procedure to identify promising fintech groups and their investment priorities. We propose a QFD-based decision support framework for banks by considering both aspects of the emerging fintech push identified using patent topic modeling and the market pull of banking services obtained from a survey of the literature and experts. An empirical application of the proposed QFD framework to major South Korean banks shows that transaction support technology, secure transactions, and trading platforms are the three most important fintech categories. The QFD results are utilized to guide individual banks for further investment strategies such as mergers and acquisitions, strategic partnerships, and spin-off operations. The proposed framework can be generalized and applied to other financial service firms.

Digital Therapeutics Product Repositioning via Multiplex Link Prediction Based on Genomic, Chemical, and Technological Information.

Digital therapeutics (DTx) companies are making efforts to expand their consumer base in the growing market. To this end, many of them reposition their existing products to identify new target diseases. In this study, we provide a link prediction framework for DTx product repositioning on the basis of a multiplex disorder network by integrating multiple data sources, such as associated genes between disorders, shared drugs, and patents of treatment protocols. To capture the disorders' latent features, both random-walk-based and deep-learning-based graph embedding methods are applied to transform the graph structure into vectors. Consequently, new indications are suggested for DTx products based on the cosine similarity between original and candidate disorders. Our framework was applied to five psychiatric DTx products to determine new target disorders that have the highest treatment potential for each product. Therefore, the study results are expected to assist DTx firms in entering the novel target market with low risk within a short period. Moreover, the applicability of DTx products to a wider variety of disorders may increase access to overall patient groups and gradually improve public health.

A credit scoring model based on the Myers-Briggs type indicator in online peer-to-peer lending.

Although psychometric features have been considered for alternative credit scoring, they have not yet been applied to peer-to-peer (P2P) lending because such information is not available on platforms. This study proposed an alternative credit scoring model for P2P lending by extracting typical personality types inferred from the borrowers' job category. We projected a virtual space of borrowers by using the affinity matrix based on the Myers-Briggs type indicator (MBTI) that fits each job category. Applying the distance in this space to Lending Club data, we used locally weighted logistic regression to vary the coefficients of the variables, which affect loan repayments, with each MBTI type for predicting the default probability. We found that each MBTI type's credit scoring model has different significant variables. This study provides insights into breakthroughs in developing alternative credit scoring for P2P lending. Supplementary Information: The online version contains supplementary material available at 10.1186/s40854-022-00347-4.

Evaluating borrowers' default risk with a spatial probit model reflecting the distance in their relational network.

Potential relationship among loan applicants can provide valuable information for evaluating default risk. However, most of the existing credit scoring models either ignore this relationship or consider a simple connection information. This study assesses the applicants' relation in terms of their distance estimated based on their characteristics. This information is then utilized in a proposed spatial probit model to reflect the different degree of borrowers' relation on the default prediction of loan applicant. We apply this method to peer-to-peer Lending Club Loan data. Empirical results show that the consideration of information on the spatial autocorrelation among loan applicants can provide high predictive power for defaults.

Recommending blue ocean technologies for subcontractors: A framework based on business reports of prime contractors and patents.

Subcontractors depend heavily on their prime contractor and thus find it very risky to enter a new business on their own. This study proposes a framework for these subcontractors to develop blue ocean technologies related to their prime contractor. First, the primary technologies predicted to be promising are extracted from the business reports of the prime contractor. Sub-technologies are then selected through a patent-based search using keywords and International Patent Classification codes of the primary technologies. From them, blue ocean technologies are proposed by optimizing the weighted mean of the min-max normalized market value, degree of competition in the technology market, and subcontractors' potential technological capabilities for each sub-technology. This study shows that subcontractors can enhance their technology competitiveness by finding a low-risk blue ocean technology. Our empirical research on the subcontractors of a semiconductor firm identified technological patent fields for them to pursue. From our framework, subcontractors can identify blue ocean technologies by considering their prime contractor's future industrial areas and technologies of interest as well as their own technological capabilities. Furthermore, the prime contractors can gain the synergy effect of technology expansion through cooperation.

Cost-benefit model for multi-generational high-technology products to compare sequential innovation strategy with quality strategy.

In the rapidly changing high-tech industry, firms that produce multi-generational products struggle to consistently introduce new products that are superior in innovativeness. However, developing innovative products in a short time sequence period is likely to cause quality problems. Therefore, considering time and resource constraints, two kinds of strategies are commonly employed: sequential innovation strategy, sequentially introducing a new generation of technology product at every launch interval, ensuring timely innovativeness but with relatively uncertain quality, or quality strategy, intermittently introducing a new generation of products, together with a derivative model between generations to enhance the quality. In this study, we propose a framework for a cost-benefit analysis that compares these two strategies by considering competition between firms within a generation as well as that within a firm across multiple generations (i.e., cannibalization) throughout the launch cycle of high-tech products. We apply our proposed framework to the smartphone market and conduct a sensitivity analysis. The results are expected to contribute to strategic decision-making related to the introduction of multi-generational technology products.

Hybrid neural network with cost-sensitive support vector machine for class-imbalanced multimodal data.

Although deep learning exhibits advantages in various applications involving multimodal data, it cannot effectively solve the class-imbalance problem. Herein, we propose a hybrid neural network with a cost-sensitive support vector machine (hybrid NN-CSSVM) for class-imbalanced multimodal data. We used a fused multiple-network structure obtained by extracting the features of different modality data, and used cost-sensitive support vector machines (SVMs) as a classifier. To alleviate the insufficiency of learning from minority-class data, our proposed cost-sensitive SVM loss function reflects different weights of misclassification errors from both majority and minority classes, by controlling cost parameters. Additionally, we present a theoretical setting of the cost parameters in our model. The proposed model is validated on real datasets that range from low to high imbalance ratios. By exploiting the complementary advantages of two architectures, the hybrid NN-CSSVM performs excellently, even with data having a minor-class proportion of only 2%.

Graph convolutional network approach applied to predict hourly bike-sharing demands considering spatial, temporal, and global effects.

Solving the supply-demand imbalance is the most crucial issue for stable implementation of a public bike-sharing system. This gap can be reduced by increasing the accuracy of demand prediction by considering spatial and temporal properties of bike demand. However, only a few attempts have been made to account for both features simultaneously. Therefore, we propose a prediction framework based on graph convolutional networks. Our framework reflects not only spatial dependencies among stations, but also various temporal patterns over different periods. Additionally, we consider the influence of global variables, such as weather and weekday/weekend to reflect non-station-level changes. We compare our framework to other baseline models using the data from Seoul's bike-sharing system. Results show that our approach has better performance than existing prediction models.

Spatial association of public sports facilities with body mass index in Korea.

Governments and also local councils create and enforce their own regional public health care plans for the problem of overweight and obesity in the population. Public sports facilities can help these plans. In this paper, we investigated the contribution of public sports facilities to the reduction of the obesity of local residents. We used the data obtained from the Fifth Korea National Health and Nutrition Examination Surveys; and measured the degree of obesity using body mass index (BMI). We conducted various spatial regression analyses including the global Moran's I test and local indicators of spatial autocorrelation analysis finding that there exists spatial dependence in the error term of spatial regression model for BMI. However, we also observed that the number of local public sports facilities is not significantly related to local BMI. This result can be caused by the low utilization ratio and an unbalanced spatial distribution of local public sports facilities. Based on our findings, we suggest that local councils need to improve the quality of public sports facilities encouraging the establishment of preferred types of pubic sports facilities.

Forecasting new product diffusion using both patent citation and web search traffic.

Accurate demand forecasting for new technology products is a key factor in the success of a business. We propose a way to forecasting a new product's diffusion through technology diffusion and interest diffusion. Technology diffusion and interest diffusion are measured by the volume of patent citations and web search traffic, respectively. We apply the proposed method to forecast the sales of hybrid cars and industrial robots in the US market. The results show that that technology diffusion, as represented by patent citations, can explain long-term sales for hybrid cars and industrial robots. On the other hand, interest diffusion, as represented by web search traffic, can help to improve the predictability of market sales of hybrid cars in the short-term. However, interest diffusion is difficult to explain the sales of industrial robots due to the different market characteristics. Finding indicates our proposed model can relatively well explain the diffusion of consumer goods.

Identifying the trends in wound-healing patents for successful investment strategies.

BACKGROUND: Recently, the need for rapid wound-healing has significantly increased because of the increasing number of patients who are diagnosed with diabetes and obesity. These conditions have contributed to a surge in the number of patients with chronic wounds worldwide. Furthermore, many cost-effective wound-healing technologies have been developed in order to keep up with the increased demand. In this paper, we performed a quantitative study of the trends associated with wound-healing technologies using patent data. METHODOLOGY: We analyzed the trends considering four different groups of patent applicants: firms, universities, research institutes, and individuals using a structural topic model. In addition, we analyzed the knowledge flow between patent applicants using citation analysis, and confirmed the role of applicants in the knowledge-flow network using k-means clustering. As a result, the primary wound-healing technology patents applied for by the four groups varied considerably, and we classified the roles of patent applicants were found in the knowledge-flow network. CONCLUSIONS: Our results showed the organizations that are leading each area of wound-healing technology. Furthermore, from the results, we identified specific institutions that are efficient for spreading knowledge related to wound-healing technology based on the patents. This information can contribute to the planning of investment strategies and technology policies related to wound-healing.

Optimal location selection for the installation of urban green roofs considering honeybee habitats along with socio-economic and environmental effects.

This study proposes a new framework for the selection of optimal locations for green roofs to achieve a sustainable urban ecosystem. The proposed framework selects building sites that can maximize the benefits of green roofs, based not only on the socio-economic and environmental benefits to urban residents, but also on the provision of urban foraging sites for honeybees. The framework comprises three steps. First, building candidates for green roofs are selected considering the building type. Second, the selected building candidates are ranked in terms of their expected socio-economic and environmental effects. The benefits of green roofs are improved energy efficiency and air quality, reduction of urban flood risk and infrastructure improvement costs, reuse of storm water, and creation of space for education and leisure. Furthermore, the estimated cost of installing green roofs is also considered. We employ spatial data to determine the expected effects of green roofs on each building unit, because the benefits and costs may vary depending on the location of the building. This is due to the heterogeneous spatial conditions. In the third step, the final building sites are proposed by solving the maximal covering location problem (MCLP) to determine the optimal locations for green roofs as urban honeybee foraging sites. As an illustrative example, we apply the proposed framework in Seoul, Korea. This new framework is expected to contribute to sustainable urban ecosystems.

Patent Network Analysis and Quadratic Assignment Procedures to Identify the Convergence of Robot Technologies.

Because of the remarkable developments in robotics in recent years, technological convergence has been active in this area. We focused on finding patterns of convergence within robot technology using network analysis of patents in both the USPTO and KIPO. To identify the variables that affect convergence, we used quadratic assignment procedures (QAP). From our analysis, we observed the patent network ecology related to convergence and found technologies that have great potential to converge with other robotics technologies. The results of our study are expected to contribute to setting up convergence based R&D policies for robotics, which can lead new innovation.

Time to death analysis of road traffic accidents in relation to delta V, drunk driving, and restraint systems.

OBJECTIVE: The main goal of this research is to identify variables related to the expected time to death due to road traffic accidents (RTAs). Such research is expected to be useful in improving safety laws and regulations and developing new safety systems. The resulting information is crucial not only for reducing accident fatalities but for assessing related insurance policies. METHODS: In this article, we analyze factors that are potentially associated with variation in the expected survival time after a road traffic accident using Weibull regression. In particular, we consider the association with alcohol involvement, delta V, and restraint systems. RESULTS: Our empirical results, obtained based on the NASS-CDS, indicate that the expected survival time for non-alcohol-impaired drivers is 3.23 times longer at a delta V of 50 km/h than that for alcohol-impaired drivers under the same conditions. In addition, it was observed that, even when occupants were alcohol-impaired, if they were protected by both air bags and seat belts, their expected survival time after an RTA increased 2.59-fold compared to alcohol-impaired drivers who used only seat belts. CONCLUSION: Our findings may be useful in improving road traffic safety and insurance policies by offering insights into the factors that reduce fatalities.

Quantification method analysis of the relationship between occupant injury and environmental factors in traffic accidents.

Injury analysis following a vehicle crash is one of the most important research areas. However, most injury analyses have focused on one-dimensional injury variables, such as the AIS (Abbreviated Injury Scale) or the IIS (Injury Impairment Scale), at a time in relation to various traffic accident factors. However, these studies cannot reflect the various injury phenomena that appear simultaneously. In this paper, we apply quantification method II to the NASS (National Automotive Sampling System) CDS (Crashworthiness Data System) to find the relationship between the categorical injury phenomena, such as the injury scale, injury position, and injury type, and the various traffic accident condition factors, such as speed, collision direction, vehicle type, and seat position. Our empirical analysis indicated the importance of safety devices, such as restraint equipment and airbags. In addition, we found that narrow impact, ejection, air bag deployment, and higher speed are associated with more severe than minor injury to the thigh, ankle, and leg in terms of dislocation, abrasion, or laceration.

A study on the student pilot's mental workload due to personality types of both instructor and student.

The main purpose of this paper is to provide the ideal flight crew combination for instructor and student pilots in order to enhance the flight training effects based on Myers Briggs Type Indicator (MBTI) theory. In addition to personality, various levels of flight difficulty are considered in order to investigate their potential interaction effect in terms of student pilots' mental workload measured in heart rate, altitude deviation, NASA-TLX (Task Load Index) and subjective degree of personality harmony. Based on an experiment performed in a real flight situation, we found significant effects of personality combinations in terms of all four outcome measures. Both group C types of instructors and students who are concrete, realistic and have mechanical skills turn out to be the ideal flight crew combination. A structural equation model, fitted to analyse causality among the four response variables, implied that as the heart rate increased, the altitude deviation increased. In addition, as the altitude deviation and personality harmony increased, NASA-TLX increased. The results of this study are expected to provide a theoretical basis for manning the flight crew combinations and thereby enhancing the efficiency of flight training.

Screening test data analysis for liver disease prediction model using growth curve.

This study was done based on screening test data accumulated from 1994 to 2001 for studying of risk factor related with liver disease and prediction model of liver disease. In the existing study related with liver, the main current is studying on liver cancer, not on liver disease, previous step into liver cancer. As a result of estimating prediction model through the risk factors of liver disease and the growth curve on the basis of data, it is shown that most of the risk factors about liver disease are also those about known well as liver cancer. In addition, to investigate liver disease prevalence from the viewpoint of the future, this study presumed risk factor through the various growth curve analysis and examined logistic regression, decision tree and neural network from those estimators. In the case of neural network using growth curve estimator of Xi(5)=alphai+betaiT+epsiloniT, accuracy of liver disease was 72.55% and sensitivity was 78.62%. On the other hand, in the case of liver disease prediction model using recent screening test data estimator, accuracy was 72.09% and sensitivity was 71.72%. Those are lower than liver disease prediction model of growth curve analysis. In the various liver disease prediction models assumed by growth curve and many distinction models, when growth curve estimator was used, sensitivity value was improved.