Ema Utami

Classifiers evaluation: Comparison of performance classifiers based on tuples amount

The aim of this study is to compare some classifiers performance related to the tuples amount. The different metrics of performance has been considered, such as: Accuracy, Mean Absolute Error (MAE), and Kappa Statistic. In this research, the different numbers of tuples are considered as well. The readmission process dataset of Diabetic patients, which has been experimented, consists of 47 features and 49.736 tuples. The methodology of this research starts from preprocessing phase. After that, the clean dataset is divided into 5 subsets which represent every multiple of 10.000 tuples randomly. Each particular subset will be validated by three traditional classifiers i.e. Naive Bayes, K-Nearest Neighbor (k-NN), and Decision Tree. We also implement some setting parameters of each classifier except Naïve Bayes. Validation method used in this research is 10-Fold Cross-Validation. As the final conclusion, we compare the performance of classifiers based on the number of tuples. Our study indicates that the more the number of tuples, the lower and weaker the MAE and Accuracy performances whereas the kappa statistic performance tend to be fluctuated. Our study also found that Naïve Bayes outperforms k-NN and Decision Tree in overall. The top classifiers performances were reached in a 20.000-tuple evaluation.

Concept and data model of AK/I card digitization as employment information distribution media

In Indonesia, AK/I card was a mandatory requirement to be owned by job seekers as a proof of identity, but the card functionality ends when the job searching process is completed and returned by the employing company to local Department of Labor. To the date this study being conducted, there was no continuity of AK/I card function relating to track record management of labor such as curriculum vitae, work experience and job preferences that could be used as an employment information distribution media and a data resource of employment figures. The current AK/I card system does not meet the need to optimally utilize Indonesias prospect of having a large power of labor force. A complex data model which is able to manage all of the data involved, including the job seekers database, job seekers competences, education histories, employment histories, companies and job vacancies would help the process. This study departed from current condition and requirement approach to propose a concept and data model for a digitized AK/I card system as an employment information distribution media. The purpose of this research is to develop a concept which offers functionality extension of the current AK/I card system to meet the modern era of data utilization. With the availability of the proposed data sets, it would be possible to do data matching calculation between job seekers and job vacancies. This paper also shows RDBMS capability to develop a data model which is able to fulfill the concept requirements.

Design concepts smartcoop with implementing financial technology

Cooperative is a democratic economic institution which conducts the activity based on the principle of kinship. Cooperatives serve savings and loans to improve the economy and welfare of society. Along with technological development, cooperatives need the services more effective and efficient in carrying out its activities. Smartcoop is an information system used to perform cooperative data management and payment transactions with implementing the financial technology therefore to enhance the active role of cooperatives. Cooperative which used Smartcoop application does not only serve savings and loans, but also payment transactions and money transfers by implementing the financial technology. Cooperative members can borrow, save money and pay the bill. In this system uses a payment provider as a transactions manager. In performing the duty, the cooperative can be monitored and controlled directly through the Smartcoop system by the Ministry of Cooperatives and SMEs. This research contains the system design architecture which is obtained from identifying problem, the design of requirement system, stakeholder, and data permission of Smartcoop application.