ANALISIS SENTIMEN TERHADAP E-WALLET DANA PADA ULASAN GOOGLE PLAY MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR

Pesatnya perkembangan teknologi saat ini yang semakin canggih menghadirkan banyak kemudahan, salah satunya terdapat cara melakukan pembayaran transaksi keuangan menjadi lebih mudah dengan aplikasi dompet digital (e-wallet). Dari beberapa produk e-wallet peneliti mengambil studi kasus yaitu produk DANA. DANA bisa diunduh pada platform android melalui google play. Google play dilengkapi fitur ulasan dan pemberian bintang sehingga para pengguna bisa melihat ulasan atau rating sebelum mereka mengunduh dari aplikasi tersebut dan dijadikan evaluasi bagi pencipta terhadap aplikasinya. Permasalahan mengenai ulasan dan pemberian bintang pada fitur google play harus dipantau dan mengorganisir opini dengan menggunakan metode atau teknis review-review tersebut secara otomatis, apakah positif atau negatif. Algoritma yang digunakan pada penelitian ini menggunakan k-nearest neighbor dengan pengujian 3 kelas berdasarkan pemberian bintang, kelas pertama terdiri dari bintang 1-5, kelas ke 2 terdiri dari (bintang 1 & 5, kelas ke 3 terdiri dari pemberian label pada bintang (1 &2 label negatif, 3 label netral, serta bintang 4 & 5 label postif) dan pengujian nilai k 1-10, sehingga didapatkan nilai accuracy tertinggi dengan kelas ke 2 dan pengujian niali k 1 didapatkan hasil accuracy sebesar 86.64%

COMPARISON OF DECISION TREE, NAÏVE BAYES, AND NEURAL NETWORK ALGORITHM FOR EARLY DETECTION OF DIABETES

Diabetes mellitus is included in the top 3 most deadly diseases in Indonesia. Based on WHO data in 2013, diabetes contributed 6.5% to the death of the Indonesian population. Diabetes is a chronic disease characterized by high blood sugar (glucose) levels that exceed normal limits. In the health sector, historical medical data can be processed to extract new information and can be used for decision-making processes such as disease prediction. This study aims to classify predictions for early detection of diabetes in order to obtain accurate results for decision making. The data used are historical data on hospital disease patients in Sylhet, Bangladesh in the form of a diabetes dataset from the UCI Repository. The algorithms used are Decision Tree, Naive Bayes, and Neural Network. Then the three methods are compared using the Rapidminer tools. The measurement results are 90% accuracy with Decision Tree, 80% with Naive Bayes, and 70% with Neural Network. So that the best algorithm is obtained, namely the Decision Tree for predicting early detection of diabetes. Rule in the form of a decision tree generated from the Decision Tree is used for input or ideas for decision making in the health sector for diabetes.

IDENTIFICATION OF THE DOMAIN PROCESS INTERSECTIONS BETWEEN COBIT 4.1 AND COBIT 5 IN THE DETERMINATION OF IT GOVERNANCE ASSESSMENT

The implementation of information technology has an essential role in organizational development to support a business process. Currently, information technology is widely adopted by the organization. It is believed to help improve the efficiency of the ongoing business process so that IT management is needed in a more structured. Thus, need a guideline that can guide IT governance so it can be measured and utilized. COBIT is one of the frameworks that can utilize in providing IT governance guidelines for organizations, and it is the main reference used in implementing IT governance in organizations. Still, the assessment process takes a long time because many processes are assessed. So conducted this research to determine the similar activities between COBIT 4.1 and COBIT 5 as the basis for determining the development of an organizational assessment process that the organization will carry out to see the efficiency of the assessed process domain. This research is focused on several organizations that have carried out IT governance assessments with COBIT 4.1 and will then implement the assessment process using COBIT 5. Still, it will usually take more time and effort if done separately to streamline the assessment process and identify domain intersects. The process from COBIT 4.1 and COBIT 5 so that the effort to carry out the assessment can be more streamlined. Thus, this research will produce a study result related to which activities intersect with each other to determine the IT governance assessment in an organization.

FEASIBILITY TEST OF POOR RICE RECIPIENTS IN BENCOY SUKABUMI VILLAGE USING NAIVE BAYES

A regional head must have a work plan every regional head must have a work plan which is sure to be of benefit to the community. Assisting is a definite work plan in every region. A lot of assistance is usually given from the government to the community and must be managed by the village government so that the aid gets to the right hands. And to improve food security, the people in each region have activities to distribute Poor Rice as a subsidy from the government. In the distribution method, sometimes there are constraints in data collection so that poor rice or what we usually call Raskin is not suitable for distribution. Because of this, a way is needed so that the distribution is appropriate or not in the community in accepting the Raskin so that government assistance can be delivered properly and on target. By using secondary data obtained from Bencoy Village, 205 data were obtained containing the attributes of the eligibility category of Raskin recipients, and 6 categories of attributes were found with the classification method of the Naïve Bayes algorithm. The accuracy value obtained is 96.59%, proving that the prediction using the Naive Bayes algorithm has a good performance. The next results obtained are in the form of AUC value which after being calculated produces a value of 0.999 and this results in an application which is an implementation with a flow that is adjusted to the calculation algorithm in the form of a web-based application.

GOVERNMENT POLICIES MODELING IN CONTROLLING INDONESIA'S COVID-19 CASES USING DATA MINING

Since the positive case of covid-19 in Indonesia, the government has taken several policies with the purpose of controlling the spread of the covid-19 virus, which has been regulated in Government Regulation No. 21 of 2020. The purpose of research is to obtain a model of government policy in controlling cases of covid by using data mining classification techniques, and obtain attributes that have the greatest weight, as well as look at the impact of policies that have been carried out by the government on the cases of covid-19 in Indonesia. The methodology used in the research is Knowledge Discovery In Database (KDD). Based on the research that has been done, it can be concluded that the policies that have been done by the government in controlling cases of covid-19 can be said to be successful, the C4.5 algorithm is the algorithm that gives the best results compared to the Deep Learning algorithm, as well as the attribute that has the greatest weight is cancel public events. Secondary data will be used in this research.

DECISION SUPPORT OF CONTRACT EMPLOYEE PERFORMANCE ASSESSMENT USING SAW METHOD AT PT. AEROFOOD ACS

Pengelolaan SDM dari suatu perusahaan sangat mempengaruhi banyak aspek penentu keberhasilan kinerja perusahaan tersebut. Jika SDM dapat di organisir dengan baik, maka diharapkan perusahaan dapat menjalankan semua proses bisnisnya dengan baik. Oleh karena hal tersebut, PT. Aerofood ACS yang memiliki banyak karyawan kontrak, perlu adanya penilaian kinerja karyawan dalam menentukan perpanjangan kontrak. Peran sistem pendukung keputusan sangat dibutuhkan guna meningkatkan efisiensi pengambilan keputusan. Dalam hal ini membantu pihak manajemen dalam mencapai tujuan dari penilaian kinerja karyawan kontrak melalui parameter-parameter yang sudah ditentukan oleh pihak perusahaan tersebut, diantaranya Discipline, Integrity, Achievement Orientation, Continnous Learning, Continunous Improvement, Quality Orientation, Customer Service Orientation, dan Teamwork. Untuk mencari solusi dalam menyelesaikan masalah tersebut, metode dalam Sistem Pengambilan Keputusan yang digunakan yaitu dengan metode Simple Additive Weighting (SAW). Semua parameter yang dinyatakan mempunyai pengaruh penting dalam penetapan alternatif keputusan terbaik dalam menentukan perpanjangan kontrak karyawan.

PIECES FRAMEWORK ON THE IMPLEMENTATION OF RAPID ENUMERATION AND EVALUATION INFORMATION SYSTEM OF 2020 POPULATION CENSUS

In September 2020, Statistics Indonesia (BPS RI) carried out a major activity, namely the 2020 Population Census At the SP2020 data processing stage, Mobile Capture is one of the options for photographing data collection results. During the use of mobile capture, BPS West Java Province encountered several obstacles. West Java Province BPS created an application called the Rapid Enumeration dan Evaluation 2020 Population Census Information System (Sicepat32 SLS) to monitor the attainment of enumeration to the smallest level (local environmental unit). To find out whether Sicepat32 SLS is working and functioning properly, it is necessary to evaluate the performance of the information system. The purpose of this study is to measure the level of user satisfaction with the application of Sicepat32 SLS and to assess whether Sicepat32 SLS can meet the needs of users. In this study, the PIECES Framework analysis model will be used and has produced an assessment score in the Performance domain of 4.07; Information and Data of 4.17; Economy 4.1; Control and Security with a score of 4.03; Efficiency with a score of 4.18 and Service getting a score of 4.18

WEB-BASED RPS MANAGEMENT INFORMATION SYSTEM (SEMESTER LESSON PLAN) USING WATERFALL MODEL

Semester Learning Plan (RPS) is a learning planning document prepared as a guide for lecturers and students in carrying out teaching and learning activities on campus for one semester. RPS was made to guide lecturers and students in the learning process so that the material taught is following the learning outcomes set by the study program. To meet and adjust the needs of graduate users and the development of science and technology, the RPS must be regularly reviewed and updated if there are changes in teaching materials that are no longer following current conditions. However, what often becomes a problem is that there is no documented process for changing the RPS content regarding the reasons and which parts have changed so that the RPS change process cannot be carried out at will and when audited there is a history of changing the data. Because of these problems, this research will design and build a web-based RPS management information system that can assist study programs in documenting RPS changes and making it easier for users to access the changed content. The system development method used in this study uses the waterfall method, and for its design using UML (Unified Modeling Language). The final result of this research is a web-based RPS management information system using the Codeigniter 4 framework which can make it easier for managers and users to obtain RPS information.

DESIGN OF AN AUTOMATIC STERILIZATION GATE TOOL USING PIR MOTION SENSOR

This automatic sterilization gate tool is a simple tool that changes the manual method to a systemized and more efficient way. This tool uses an infrared motion sensor in which there is a main component, namely the PIR (Pyroelectric Infra-Red) sensor, which is a material that reacts to radiation and movement in front of it. This tool also uses a 12v dc pump which is used to draw out the disinfectant liquid stored in the container. This gate tool is designed using the main material and some additional materials, the automatic gate can discharge about 11 seconds of liquid from objects or people that pass through the sensor range, 11 seconds is the minimum time for this tool to work while a distance of 6 meters is the range from where the sensor is located. From that time it proved that this gate tool has 100% accuracy and runs well. This gate tool is used every day, turned on from the morning, and turned off at night. Every 17.00 hours this gate tool is always replenished with supplies of disinfectant liquid. The automatic gate has helped the community to reduce the risk of transmission of the coronavirus, it also raises the awareness of the covid-19 pandemic. The whole system is implemented and is tested for real-time operation. It is found working satisfactorily. The gate tool can be further improved by adding a scanning device to perform tracing for passersby.

TELEMARKETING BANK SUCCESS PREDICTION USING MULTILAYER PERCEPTRON (MLP) ALGORITHM WITH RESAMPLING

Telemarketing is a promotion that is considered effective for promoting a product to consumers by telephone, other than that telemarketing is easier to accept because of its direct nature of offering products to consumers. Telemarketing is also considered to help increase a company's revenue. The problem of predicting the success of a bank's telemarketing data must be done using machine learning techniques. Machine learning used in the available historical data is a bank dataset of 45211 instances at 17 features using the multilayer perceptron algorithm (MLP) with resampling. The use of resampling aims to balance the unbalanced data resulting in an accuracy value of 90.18% and a ROC of 0.89%. Meanwhile, if the data resampling is not used in the multilayer perceptron (MLP) algorithm, the accuracy value is 88.6 and ROC is 0.88%. The use of resampling data becomes more effective and results in higher accuracy values.