Search

The culinary industry is a business that is experiencing very fast growth. Technology simplifies all activities in management so that data presentation is faster and more accurate. The application of technology helps increase the effectiveness of the business processes being carried out. The restaurant business in using technology is needed to simplify the ordering process, submit data, process payments, make reports more innovative and efficient. This application was developed using agile method as needed which has many changes. This development simplifies the process of customer ordering and payment transactions for satisfaction with the service system provided so as to improve performance more effectively and efficiently.

For the formation of prosperous citizens, it is necessary to have good management in service to residents, one of which is the financial management of the Rukun Warga (RW) which contains community contributions for payment along with income and financial expenditure reports. This problem is currently being faced by residents and treasurers in the RW environment. 001 Rawajati Subdistrict, Pancoran Subdistrict, it is difficult to find data and payment reports that are not neatly arranged considering the large number of residents who make payments every day because the payment process is still very simple and you cannot see anything. It's just that fees that have been paid or those that haven't been paid, especially during this pandemic, people prefer to use digital transactions compared to manual or using cash. The benefits of this research, in the research methodology that will be carried out using methods of literature study, interviews, and observation. The author designs and builds a website-based accounting information system and the Codeigniter framework that involves 2 system users, namely residents and treasurer. Residents can view bills, make contribution payments, view the history of bills that have been or have not been paid, and reports on financial expenditures, namely the treasurer as a user who is currently inputting citizen data, citizen contribution billing data, and inputting financial expenditure reports. The results of this study can handle the entire process of recording administrative transactions from incoming fees incurred to preparing transaction reports to obtain more accurate information. The test results use the System Usability Scale (SUS) method with an average SUS score of 77.9 and it is certain that the respondents agree with the application of management accounting in RW 001

Health is the basis of the level of humanity. However, in reality, not everyone with social welfare problems has national health insurance. The large number of patient files that must be checked makes it difficult for officers to identify potential beneficiaries. Based on these problems, a procedure or method is needed that can assist officers in identifying potential beneficiaries. From the results of the performance testing of the two models using a confusion matrix with 730 records used as training data and 313 records used as test data, the C4.5 classification algorithm gets the highest accuracy value, which is 99.04%. A total of 310 data records were predicted correctly with an error rate or error of 0.96% or as many as 3 data records from 313 data tested. While the Naive Bayes classification algorithm gets an accuracy value of 92.97%. A total of 291 data records were predicted to be correct with an error rate of 7.03% or as many as 22 data records were predicted to be incorrect from the 313 data tested

Information Technology has played an important role as a medium of information and communication in the field of education, one of which is in the Academic Management of Schools. In the world of educational technology it is not only related to the internet but can also be seen from the system or how to teach in schools. At present, the learning process using E-learning can be interactive so that students are able to interact with technology as a learning medium. Web-based learning media (e-learning) is a web that can help educators in the rapidly developing era of information and communication technology development. In this research, the problem that arises in the school environment is that there is no special place for students and teachers to be organized in obtaining learning materials and collecting assignments, documentation of knowledge of learning materials that are not stored properly, so it takes a long time to find the required knowledge back. Therefore used data collection methods, namely the method of observation, interview methods (interviews), and literature study. The Agile method is the most appropriate method used to design this system with the aim that the author can help ease the task of students and teachers in carrying out their duties. The results achieved in making the e-learning application at SDN Tengah 01 KramatJati are that students can understand material without a time limit, consult, take quizzes, upload assignments and can immediately see their learning results in person, while teachers can upload material, create questions and give them directly live.

Indonesia is included in the category of countries with the largest population in the world, this situation is a business opportunity for entrepreneurs who enter the coffee shop industry market. Researchers utilize one of the grouping methods, namely data mining classification in order to help business entities to identify different groups in the Starbucks customer satisfaction database. The purpose of this research is to be able to group categories into 3 classes, namely satisfied, quite satisfied and dissatisfied using the Decision Tree & Naive Bayes algorithm. So that it can find out public opinion on Starbucks customer satisfaction, in this study the aim was to obtain accuracy, precision and recall values and find out the best algorithm for data mining classification of Starbucks customer satisfaction. In this study using test data obtained from tweets with the keyword "Starbucks" from Twitter. The results of this study where the sentiment classification process for Starbucks customer satisfaction obtained a neutral category, it can be seen from the reviews using the keywords "starbuck OR starbucks OR #starbucks "The results obtained were positive comments of 476 tweets with a percentage of 19.2%, neutral comments of 1743 tweets with a percentage of 70.3% and negative comments of 258 tweets with a percentage of 10.4%, so that conclusions can be drawn based on the polarity calculation, the comments on stabuck have a satisfied category.In this study, it can be concluded that the performance of the Decision Tree algorithm is better than the Naive Bayes algorithm, as can be seen from the following explanation.The Decision Tree algorithm results in an accuracy of 83%. Naïve Bayes on value accuracy results by 74%.

In the business world, choosing the right business location is one of the main things that must be considered, the problem that occurs is choosing a business location that is not right for the business actors themselves. Therefore, an application is needed that helps business actors to determine the location. strategic for the business they are involved in. In this research, a decision support system application was made to make it easier for business actors to determine the location according to the criteria. Decision support applications are considered effective enough to create a ranking in determining strategic locations for business actors. The Weighted Product and SMART methods using 7 alternative data shows that the two methods produce data that is accurate and suitable when applied as a ranking for selecting business locations. The 2 methods have an elective execution score and the results of the weight values applied to each technique.

Social media used in communicating that is very popular in Indonesia. One of the most popular is Twitter. Twitter is a social media site where people can share information publicly. This information can be processed to make sentiment analysis. This research attempts to create a system that can detect positive or negative sentiments in public information. The method used for this sentiment classification is the comparison method of Naive Bayes Classifier and K-Nearest Neighbor Classifier using TF-IDF weighting. The input to this system is in the form of tweet data for Transjakarta, while the output of this system is in the form of visualization of positive and negative sentiment data using Streamlit which is a library from python. Based on testing the accuracy of the Naive Bayes approach for sentiment analysis of Twitter data related to the use of Transjakarta transportation is 61.1%, and the accuracy of the K-Nearest Neighbor method is 75.7%. For the two methods used in determining the level of accuracy, it can be concluded that the K-nearest-neighbor method produces better accuracy.

Petshop is a place of business that sells pet needs and supplies. Cora Petshop, whose head office is at Jalan. Batu Raya 1 No.9 Setiabudi, South Jakarta is a shop that sells animal supplies and needs that started a business in 2020 through online media. In the online trading system, it is considered risky and becomes a consideration for consumers in making purchases. One of the main factors of business success is from customers. This is the basis for Cora Petshop to run its business face to face. Point of Sale is one of the many systems used as a means of payment in various existing businesses. Transaction activities between the Point of Sale System and customers that occur in the business world. In this study, a Point of Sale system application has been made for business support for Cora Petshop, with the system development method using Agile Software Development along with the Scrum framework contained in Agile techniques. The results that are applied to the Point of Sale are successful in making transactions, recording incoming and outgoing reports of goods, and are suitable for use.

Penyakit jantung merupakan penyebab utama kematian yang menduduki peringkat satu di Indonesia. Oleh karena itu, dokter perlu mendeteksi sejak dini penyakit jantung pada pasien. Dalam mendiagnosa penyakit jantung diperlukan sebuah alat untuk mengetahui kondisi fisik jantung. Alat yang sering digunakan adalah Elektrokardiogram (EKG). Alat EKG ini dapat memantau aktivitas listrik jantung yang ditampilkan dalam bentuk grafik. Namun, alat EKG ini dinilai belum mampu mendeteksi secara otomatis keadaan jantung pasien. Oleh karena itu, pada penelitian ini dikembangkan sebuah aplikasi untuk mengidentifikasi kelainan jantung secara otomatis berbasis metode Fuzzy Mamdani dengan menggunakan 100 data hasil rekam medis Elektrokardiogram. Sistem yang dikembangkan mampu mengidentifikasi kondisi jantung pasien dalam dua kategori yaitu kondisi jantung yang normal dan kondisi jantung yang abnormal. Adanya sistem ini dapat membantu dokter dalam melakukan pemeriksaan kondisi jantung. Berdasarkan hasil pengujian sistem dengan pendekatan success rate mendapat nilai True positive 0,9%, nilai False Positive 0%, nilai success rate sebesar 95%, dan nilai error rate sebesar 0,05 %.Heart disease is the number one cause of death in Indonesia. Therefore, doctors need to detect early heart disease in patients. In diagnosing heart disease, a tool is needed to determine the physical condition of the heart. The tool often used is the electrocardiogram (EKG). This EKG tool can compile the heart's electrical activity, which is displayed in graphic form. However, this EKG tool cannot detect the patient's heart condition automatically. Therefore, this study developed a system to detect cardiac abnormalities using the Fuzzy Mamdani method using 100 electrocardiogram medical record data. The developed system can identify the patient's heart condition, namely normal heart and abnormal heart conditions. The existence of this system can assist doctors in examining heart conditions. Based on the results of system testing using the success rate approach, a True positive value of 0.9%, a False Positive value of 0%, a success rate of 95%, and an error rate of 0.05%.

The limitations of medical personnel, especially heart disease, cause difficulties in diagnosing heart disorders, so diagnosing heart disorders is not easy, it takes the ability and experience of a cardiologist who has the expertise and experience to be able to accurately diagnose heart disorders. Several studies in the field of computing have been carried out in diagnosing cardiac abnormalities in patients. This study was conducted to accurately test the results of the classification of heart disorders using electrocardiogram medical record data with a C.45 decision tree approach. The results showed that the classification of heart defects obtained a mean squared error (MSE) value of 0.24, a root mean squared error (RMSE) value of 0.49, and an accuracy value of 75.33% with the C4.5 algorithm.

Supervisors are direct supervisors of leaders and operators who have duties and responsibilities, namely providing direction or work planning in accordance with existing SOPs in the company and monitoring the work of leaders and operators properly. In this study, so far the company in evaluating the performance of the supervisor is done manually, that is, the company only judges based on the length of time the supervisor has worked. In fact, the supervisor's performance appraisal is an ineffective performance appraisal. Therefore, the company must make several other performance assessments such as Length of Work, Leadership, Communication, Discipline and Attendance. In evaluating the supervisor's performance, a decision support system (DSS) is needed. The method used in this study is the COPRAS method with ROC weighting. The calculation of the COPRAS method with ROC weighting can produce the best alternative, namely alternative A2 on behalf of "Budiman Sianipar, ST" with a value of Ui = 100

As the industry grows, the competition for superior products in this region is getting tougher. This competition will force all industries to pay more attention to policy making. Decision making to prioritize the best regional products according to needs and capabilities requires accurate and effective decisions to make the right choice and minimize losses in both cost and time. With the problems mentioned above, local governments (PEMDAs) are bothered with determining the priority of regional superior products quickly and precisely. Therefore, to determine the priority of regional superior products, a decision support system is needed to facilitate work and avoid errors in calculating system data quickly and more accurately. The Rank Order Centroid (ROC) and Multi Attribute Utility Theory (MAUT) methods are a combination of methods that support in determining the priority criteria for regional superior products. The results of the application of the combination according to the formulas and methods used to obtain the highest value alternative are Coffee products with the first rank, namely 0.00653.

IDS Education is an online course application. users or users can follow the various classes available in the application. These classes have a variety of class choices offered and the class learning is fully online making it easier to do learning anywhere and anytime. to maintain a positive image of the application, a usability evaluation of an application display and user comfort in using the application is made. The evaluation aims to measure the level of satisfaction for users of the IDS Education application. there are two methods used, namely End-User Computing Satisfaction and PIECES. Both methods are used to find the level of user satisfaction. the End User Computing Satisfaction got a score of 4,498 with a very satisfactory level of user satisfaction. and for the PIECES method to get a score of 4.38 with a very satisfying level of user satisfaction. besides that, it also uses the PageSpeed Insights tool to assess the performance of the homepage on the IDS Education application. The Performance value obtained on PageSpeed Insights is 78, this shows that the homepage has a pretty good Performance.

Along with the current development of digitalization technology, almost all aspects have adapted to these changes, including the Indonesian people, who are mostly traders, also take part in this development. The website is one of the digitalization models that is often used in promoting products, both goods and Services, in this case the author takes one example, namely the sale of a flower shop "Bunds Flowers" where in this case the flowers that are sold are not like flowers in general, but there are flowers in the type of paper, plastic, to imported and local flowers, making this flower shop very worthy of having more promotional value, both in terms of conventional (face-to-face) and modern (online/digitalized) sales. This study uses two methods where the waterfall method is applied to the system development process and the PIECES method to analyze the user's response to the system that has been built. In this journal the author aims to build a system where sales and ornamental plant enthusiasts still use traditional media, with the websites help consumers find what they need in an easy way by opening a website. In the analysis process, the respondents have produced several assessments related to the flower shop application, including 1) performance, respondents rated 3.73 (Satisfied) 2) Information, respondents rated 4.33 (Satisfied), 3) Economic, respondents rated 4.33 (Satisfied) , 4) Control and Security, respondents rated 4.10 (Satisfied) and 5 Efficiency, respondents rated 3.73 (Satisfied) and Service, respondents rated 3.73 (satisfied).

The purpose of this study is to design and develop a stunting symptom detection system in children using the Website-based certainty factor method which aims to create a stunting symptom detection system in children from an early age and help parents in maintaining nutrition in their children, indirectly said to be computerized to detect stunting means that when applied, it makes it easier for parents to monitor nutrition quickly and precisely. This study uses a system development method where the model used is Waterfall. The results of this study are in the form of an application that provides several symptoms of stunting in children then the user can conduct consultations to determine the calculation of the results of stunting symptoms correctly. The use of this certainty factor method is implemented in an expert system that is used to look for symptoms caused by stunting and in solving the case, the certainty factor obtains an accuracy of 80%.

Social media is one of the technological developments that has contributed greatly in making it easy for us to communicate and socialize, one of which is using Twitter social media. Twitter in this study is used as a data source to analyze tweets discussing KRI Nanggala 402. Analysis of KRI Nanggala 402 twitter sentiment is used to see the tendency of public responses to the sinking of the KRI Nanggala 402 submarine whether to give positive or negative opinions. This Sentiment analysis uses the Naïve Bayes Classifier method, which is a classification method. The first research stage is crawling, processing, classification, and evaluation. The classification stage is carried out after the processing phase, where the classification results tend to be positive or negative, using the Naïve Bayes Classifier method. The accuracy of the system in the Sentiment analysis of the KRI Nanggala 402 tweet is 73.00%.

Asian Arowana fish are freshwater fish that are spread across Southeast Asia. Many Indonesian people maintain Arowana fish because of its beauty and also has a high enough price. But in the process of cultivation, the Asian Arowana Fish can be attacked by more than one disease that can threaten the survival of the Arowana fish. With the rapid advancement of technology that is taking place and based on these problems, the author implements an Expert System to detect what diseases attack these fish with symptoms and data obtained from experts so that we know what steps must be taken for the prevention and sustainability of Arowana fish cultivation. The method used is the Naïve Bayes Method, which is a probability statistical method that can detect whether a fish is exposed to a disease with pre-existing web-based odds.

Tiara Brand is a self-produced clothing business. The process of selling products at Tiara Brand is done by promoting their products through social media. This process is considered less effective, because customers have to order through another application, namely WhatsApp. Business owners also find it difficult to promote their products widely. Based on these problems, this study will discuss the design and creation of a website-based e-commerce application using the CodeIgniter framework, so that it is easier for customers to buy products from Tiara Brand, because it can be done on the same website. In addition, business owners can also more easily manage each transaction and can promote their products to customers without regional restrictions. the steps of this research are made in the form of a flowchart and go through stages consisting of; 1) Data collection, 2) Literature study, 3) Design, 4) Program code preparation, and 5) Application testing and using the String Matching Algorithm as an implementation of the application being built. The results of the research are the construction of a website that not only displays the products being sold, but can also be used for transactions and has the potential to develop Tiara Brand selling online.

The purpose of this study is to obtain the results of the analysis of factors that make prospective customers who want to open an account at a branch switch to opening an online account. This study uses the K-Means method and uses the age factor, the time period in opening an account as a parameter. The data collection technique is in the form of data collection by questionnaire. The subject of this research is marketing who are members of PT Dika in collaboration with PT Bank Central Asia. Based on the research conducted by the author using the K-Means Clustering method and the rapidminer application, the researchers drew the following conclusions; 1) Of the three clusters, the age factor that has the most value is at age 21 in cluster 3 as many as 3 people. As for the age of 22 to 26 in the three clusters, the three clusters are not much different, 2) Of the three clusters, the most income factors are in group 3 as many as 4 people in cluster 2, namely earning around 1.500.000 – 3,000,000, 3) Of the three cluster, the distance factor from home to the nearest BCA Bank is at most at distance 1 as many as 3 people in cluster 3 and at distance 3 as many as 3 people in cluster 2, 4) Of the three clusters, the processing time factor is mostly in group 1 as much as 3 people in cluster 1, group 2 as many as 3 people in cluster 3 and group 3 as many as 3 people in cluster 3, and 5) From the three clusters, the factor of moving from opening an account at a branch to opening an online account (pemol) is because it's faster, in cluster 1 as many as 3 people, in cluster 2 as many as 2 people and in cluster 3 as many as 3 people.

This research was conducted because of the trend that has occurred in the last 5 years in Indonesia, namely the emergence of mobile -based game s that are played by many people in Indonesia from small children to adults. With the emergence of mobile -based game s in Indonesia, the appeal of PC and console-based game s has become less attractive. This study aims to analyze the factors that influence PC and console-based gamers to switch to mobile -based game s. The method used in this study is K-means Cluster ing and the supporting data from this study include the age factor of the game players and the duration of playing the game as a parameter. The technique of collecting data is through a google form questionnaire. The subject of the research is the Indonesian gamers forum contained in facebook forums.

The implementation of paying zakat is obligatory for every Muslim. Generally, there are problems that are lacking in the recording of zakat management. Currently, many still use the manual method which is of course very risky for loss and damage to the recording of zakat. Therefore, the purpose of this study is to design a website that facilitates the payment and recording of zakat. With this research, it is expected to ease the mosque management to manage zakat to be more efficient. In this study applying the Agile SDLC model, this study has four stages, namely, timebox planning, iteration, demonstration, and retrospective meeting. Based on the research that has been done, namely the Implementation of Agile Methods on a Website-Based Zakat Management System with the Laravel Framework at the Al-Ijabah Mosque Amil Zakat Agency, the researcher concludes that the system built has met the administrative needs to input data such as Muzakki data (zakat givers). , Mustahiq data (zakat recipients), daily transaction reports. With the construction of this system, zakat transaction data can be stored in the database. So that zakat transaction data is not easily lost/damaged.

Melewati setahun sejak dimulainya pandemi Covid-19, telah banyak memakan korban dan mengubah cara manusia dalam berinteraksi dan menavigasi dunia. Meskipun penggunaan vaksin diterapkan, tetapi tetap saja jumlah korban terus bertambah di dunia. Informasi tentang data Covid-19 tersebar di setiap negara, sehingga perlu wadah untuk melihat data tersebut secara cepat, akurat dan fleksibel antar aplikasi. Dengan menggunakan metode API atau Application Programming Interface, dapat diperoleh data tersebut melalui internet. Pada tahapan penelitian dilakukan melalui perencanaan sistem, pengumpulan data, dan analisis data. Dari hasil penelitian diketahui bahwa Power BI mampu menarik dan mengolah data API Covid-19 menjadi berbagai macam grafik. Kemudian dari hasil grafik-grafik tersebut dapat disimpulkan bahwa untuk total kasus, total total sembuh dan total meninggal untuk tertinggi dipegang oleh negara USA (Amerika Serikat). Untuk total kasus baru tertinggi oleh negara India. Kemudian untuk tertinggi bagian persentase total kasus berdasarkan benua dipegang oleh benua Asia.

The COVID-19 outbreak has reached the entire world, including Indonesia. With a pandemic like this, traveling out of town will experience difficulties because the government has issued a policy for the public to carry out a Rapid Test Antigen so that they can travel outside the city, and in the midst of a pandemic like this, all hospitals do not necessarily provide a Rapid Test Antigen. In this study, the authors created a website that contains information on hospitals that provide Rapid Test Antigen in Jakarta with the SDLC (System Development Life Cycle) method. The are used for this research is the entire DKI Jakarta area. The study uses data collection techniques by surveying directly to a hospital that provides the Rapid Test Antigen and secondary data obtained from the internet media. This application is expected to make it easier for residents of DKI Jakarta and those from outside the city to find out the location that provides the Rapid Antigen Test in Jakarta.

Corona Virus Disease atau lebih dikenal Virus Corona telah menyerang ke seluruh penjuru dunia tidak terkecuali Indonesia. Sudah hampir +1 tahun virus ini masih menyerang Indonesia dan berdampak di berbagai sektor bidang, salah satunya bidang pendidikan. Demi menanggulangi penyebaran virus, pemerintah menetapkan sistem pendidikan dilaksanakan secara online. Banyak keluh kesah yang dialami mahasiswa terutama mahasiswa yang pulang kampung, banyak yang dialami mereka mulai kesulitan akses internet, tugas yang harus diselesaikan begitu banyak dan masih banyak lagi. Adapun tujuan dari penelitian ini yaitu untuk mendapatkan ketepatan hasil klasifikasi berdasarkan tingkat akurasi dari persepsi mahasiswa yang menggunakan twitter mengenai pemberlakuan kuliah secara online. Dalam penelitian ini ada tiga metode yang akan dipakai untuk proses klasifikasi. Metodenya tersebut yaitu Naive Bayes, KNN dan Decision Tree. Data yang dipakai dalam penelitian ini merupakan data twitter  yang diambil dengan cara crawling data. Dari hasil pengujian diketahui metode Decision Tree memiliki nilai yang lebih tinggi diantara metode lainnya dengan akurasi sebesar 61.92%, presisi 73.63%, dan recall 11.42%.

The Covid-19 pandemic that has occurred since 2020 entered Indonesia and has almost occurred in all parts of the world has resulted in the world being stopped due to the Covid-19 Pandemic, all its effects have been felt by all circles, one of which is business actors. Indonesia is one of the countries affected by the Covid-19 Pandemic, one of which is the Indonesian economy which is in the MSME business sector, especially the Micro sector, such as the perfume business, clothes distro, shoe shop, medium-scale traders. small down another. They are most affected by this Pandemic because since the implementation of the large social scale (PSBB) which has automatically reduced their sales turnover. Because consumers no longer come to them. Therefore, the authors created a website-based system to assist MSMEs in making sales. Which is where the buyer no longer has to come to the seller. The author hopes this website can help return to their sales turnover.

The emergence of a habit in Indonesia and even the world, namely the use of used clothes (thrifting) became the idea for this research. This new habit is known to be able to reduce the production of textile waste in the world. The purpose of this study was to obtain analysis results that affect the use of new clothes (fast fashion) on the use of used clothes (thrifting). Using the K-means Clustering method and using several parameters, including age, quality, price, and sustainability or awareness. The method of collecting data is through a questionnaire and the research material is the buyers found in the online store Instagram (thriftboys.id). From the results of the clustering process that researchers have done using the K-means algorithm with manual calculations and rapidminer applications, the conclusions consist of; 1) In clusters 1 and 2 the age factor shifting from fast fashion to thhirft is 23 years, while in cluster 3 it is 25 years, 2) In the three clusters the average income that shifts from fast fashion to thhirf is group 3 or the range of 200000 -500000, 3) In the third cluster, people switch from fast fashion to thrift because of the good quality of goods, and 4) In clusters 2 and 3 more people are aware of textile waste for the world. Meanwhile, cluster 1 has the same number of conscious and unconscious waste.

The presence of the Covid-19 pandemic outbreak makes consumer behavior in shopping began to change. Especially when the enactment of large-scale social restrictions (PSBB) regulations. Providing food service in this place cannot be expected to return. So, the divisions will not think of out of the house just eating in restaurants or eating places. One marketing strategy in the current era offers a message of delivery, this strategy can help remain to comply with regulations that apply during the Pandemic Covid-19. This study aims to obtain the results of the analysis that influences the level of public interest in the purchase of online-based foods, namely by (Food Delivery). This study uses the K-means method and uses the name, age, income, number of orders, order intensity, and satisfaction. This study uses several data collection techniques questionnaire. The subjects of this study are buyers who are members of the Food Delivery Instagram (Bellyboys.id) forum.

The purpose of this study was to determine the results of the analysis of the final project document for students majoring in information systems, National University. The research data is grouped based on the theme, object and research method. In this study, the K-Means Clustering method will be used which in the data includes the type of final project, year of publication and reasons for selecting the data. The data collection technique was chosen from the thesis document. The subjects in this study were part of the document that was processed in the abstract. Based on the results of the Clustering process above using the K-means algorithm method and the rapidminer application, it is concluded; 1) In the three clusters, it shows that the final project data 1 has 3 data, the final project 2 has 5 data, the final project 3 has 3 data and the final project 4 has 5 data., 2) In the three clusters the data is the most years old. group 3, namely in cluster 2 there are 3 data, cluster 3 there is 1 data, 3) In the three clusters, it shows that the data for the selection of 3 at least in cluster 2 there is 1 data.

The objectives of this research are; 1) Can find the results of the analysis of switching factors, namely the age data, and 2) Can find the results of the analysis of switching factors, namely the data on the travel time of public transportation, 3) Can find the results of the analysis of switching factors, namely the data on the travel time of Go-jek 4) Can find the results of the analysis of switching factors, namely the tariff data, and 5) Can find the results of the analysis of switching factors, namely the data that is easy to obtain. This study was designed to determine the results of the analysis of factors that influence the shifting of public transportation to Go-jek online transportation using the K-means clustering algorithm. The data collection technique in this study was by means of a questionnaire through the Go-jek community in Indonesia and secondary data taken from the internet media. Based on the results of the analysis that has been carried out on the analysis of factors that influence public transport passengers to switch to Go-jek online transportation using the K-means clustering algorithm, it is hoped that further researchers will test with other clustering algorithms, and the rapidminer software used as research material can be developed further. become more other features.

Armada kendaraan truk merupakan salah satu aset utama dalam bisnis di bidang jasa transportasi. Evaluasi kinerja amada secara cepat dan akurat diperlukan untuk mendukung tercapainya produktivitas armada secara maksimal sehingga target perusahaan dapat mudah tercapai. Proses evaluasi kinerja armada yang masih dilakukan secara manual menyebabkan rumitnya proses pengolahan dan kurang akurat nya hasil evaluasi yang diperoleh, sehingga diperlukan suatu teknik pengolahan data secara cepat dan lebih akurat salah satunya dengan namun menerapkan teknik data mining menggunakan metode clustering. Metode Clustering akan digunakan untuk mengelompokkan setiap armada kendaraan berdasarkan produktivitas kinerjanya. Penelitian ini membandingkan penerapan Algoritma K-Means dan K-Medoids, yang kemudian dilakukan uji validitas terhadap hasil cluster yang terbentuk. Davies Bouldin Index sebagai metode dalam analisis klaster menghasilkan nilai validitas sebesar 0,67 untuk K-Means clustering dan 1,78 untuk K-Medoids. Berdasarkan nilai validitas yang dihasilkan Algoritma K-Means dipilih untuk diimplementasikan pada pembuatan aplikasi clustering armada kendaraan berbasis web karena paling relevan dengan nilai validitas DBI yang lebih rendah dari pada K-Medoids. Pengujian yang telah dilakukan terhadap hasil clustering pada aplikasi web didapatkan persentase kesesuaian sebesar 97 % baik dengan tool Rapidminer maupun dengan perhitungan secara manual