Hasil Pencarian  ::  Simpan CSV :: Kembali

"

Transaksi kartu kredit yang semakin meningkat yang diikuti dengan maraknya tindak kecurangan memicu penelitian mengenai pengembangan model prediksi transaksi kartu kredit fraud. Data transaksi kartu kredit Doku digunakan menjadi sumber data pada penelitian. Penelitian ini melakukan pengembangan model prediksi serta webservice prediksi transaksi kartu kredit fraud. Fitur yang digunakan dalam pembuatan model adalah amount, payment bank issuer, payment bank acquirer, payment brand, payment 3D secure ECI, payment type, payment bank issuer country, dan hour. Model Decision Tree memberikan hasil terbaik dalam aspek precision dan F1-score dengan nilai 97.2% dan 96.8%. Model XGBoost memberikan hasil terbaik dalam aspek recall dan FP-rate dengan nilai 96.4% dan 3%. Kedua model tersebut sama-sama memperoleh nilai accuracy terbaik yaitu 96.7%. Dalam aspek webservice, model XGBoost memiliki performa terbaik dengan rata-rata throughput 77 request per detik.

---

The increasing amount of credit card transaction followed by fraudulent transaction becoming more rampant provokes many studies in fraud credit card transaction prediction model. Doku credit card transaction is used as data source for this study. This study experiments on developing model and webservice to predict fraud credit card transaction. Features used in builiding the model are amount, payment bank issuer, payment bankacquirer, payment brand, payment 3D secure ECI, payment type, payment bank issuer country, and hour. Decision Tree model achieves best precision and F1-score with 97.2% and 96.8% score. XGBoost model achieves best recall and FP-rate with 96.4% and 3% score. Both said model achieves same best accuracy with 96.7% score. In regards of the webservice, XGBoost achieves best performance with average throughput reaching 77 request per second.

"

"PT Nusa Satu Inti Artha atau lebih dikenal dengan DOKU merupakan salah satu perusahaan fintech yang bergerak di sektor pembayaran. DOKU telah digunakan oleh lebih dari 100.000 merchant online dalam kedua layanannya, yaitu payment gateway dan transfer service. Semakin banyaknya merchant yang melakukan registrasi, menuntut DOKU untuk lebih efisien dalam menjalankan salah satu tahapan pada proses registrasi tersebut, yaitu verifikasi situs merchant. Penilitian ini memiliki tujuan untuk mengem- bangkan sebuah aplikasi web crawler yang dapat digunakan untuk melakukan ekstraksi kelengkapan data situs merchant dan melakukan prediksi tingkatan fraud situs tersebut secara otomatis. Web crawler dibuat menggunakan micro web framework bernama Flask dan berisi modul-modul yang dapat melakukan ekstraksi fitur-fitur untuk kemudian dilakukan scoring menggunakan model machine learning yang diimplementasi di dalamnya. Pemilihan model dilakukan dengan cara melakukan nested cross-validation terhadap empat jenis classifier, yaitu Decision Tree Classifier, Random Forest Classifier, Extreme Gradient Boost Classifier, dan Bernoulli Naive Bayes Classifier. Hasil analisis menunjukkan bahwa Bernoulli Naive Bayes Classifier memiliki hasil performa terbaik, sehingga classifier ini juga yang akan diimplementasikan pada web crawler. Hasil dari pengembangan web crawler menunjukkan bahwa efisiensi waktu proses verifikasi dapat ditingkatkan sebesar 4900% dengan AUC sebesar 0.953 dan recall sebesar 0.864.

---

PT Nusa Satu Inti Artha or better known as DOKU is one of the fintech companies engaged in the payment sector. DOKU has been used by more than 100,000 online mer- chants in its two services, namely payment gateway and transfer service. More and more merchants are registering, demanding DOKU to be more efficient in carrying out one of the stages in the registration process, namely merchant site verification. This research aims to develop a web crawler application that can be used to extract the the merchant site data and to predict the fraud level of the site automatically. Web crawler is created using a micro web framework named Flask and contains modules that can extract features to then do scoring using the machine learning model implemented in it. Model selection is done by doing nested cross-validation of four types of classifier namely Decision Tree Classifier, Random Forest Classifier, Extreme Gradient Boost Classifier, and Bernoulli Naive Bayes Classifier. The analysis shows that the Bernoulli Naive Bayes Classifier has the best performance results, so this classifier will be the one that implemented on the web crawler. The results of the development of web crawler show that the efficiency of the verification process can be increased by 4900% with AUC of 0.953 and recall of 0.864."

"Jenis usaha perasuransian PT XYZ dibagi menjadi dua yaitu asuransi kesehatan dan asuransi jiwa. Salah satu risiko yang terjadi dan berdampak pada kerugian perasuransian adalah kecurangan atau fraud yang dilakukan pihak tertentu untuk memperoleh keuntungan sepihak. Penelitian ini dilakukan untuk membuat pemodelan data mining yang digunakan untuk mendeteksi fraud pada asuransi kesehatan. Tujuan dari penelitian ini adalah memperoleh algoritma model berbasis data mining yang dapat mendeteksi fraud pada transaksi klaim peserta di PT XYZ. Karakteristik data yang digunakan bersifat imbalanced, karena jumlah data fraud yang digunakan tidak sebesar jika dibandingkan dengan data yang bersifat normal. Pembentukan model pada penelitian ini dilakukan dengan 32 skenario, dengan hasil terbaik skenario dengan penerapan feature engineering, feature selection, oversampling dan uji validasi menggunakan 20­-fold cross validation. Adapun hasil dari skenario tersebut menghasilkan algoritma random forest yang memiliki nilai akurasi paling baik yaitu 99,3% dengan didukung oleh nilai presisi, recall, dan f1 scores masing-masing, 99,3%, 99,3%, dan 99,3%. Hasil akhir dari penelitian ini memperlihatkan bahwa teknik feature engineering dengan penambahan atribut is_dr_speciality, memiliki kontribusi terhadap nilai akurasi model.

---

The type of insurance business of PT XYZ is divided into two, namely health insurance and life insurance. One of the risks that occur and impact insurance losses is fraud committed by certain parties to obtain unilateral benefits. This research was conducted to create a data mining model used to detect fraud in health insurance. The purpose of this study is to obtain a data mining-based model algorithm that can detect fraud in participant claims transactions at PT XYZ. The characteristics of the data used are imbalanced because the amount of fraud data used is not as much as compared to normal data. The model formation in this study was carried out with 32 scenarios, with the best results being the scenario by applying feature engineering, feature selection, oversampling, and validation tests using 20-fold cross-validation. This scenario resulted in the random forest algorithm having the best accuracy value of 99.3%, supported by precision, recall, and f1 scores, 99.3%, 99.3%, and 99.3%. The final result of this study shows that the feature engineering technique with the addition of the is_dr_speciality attribute has contributed to the model's accuracy value."

"Bank adalah salah satu industri keuangan. Sebagai industri keuangan yang melayaninasabah, ada risiko yang terjadi pada bank. Salah satu risiko yang sering terjadi danmenyebabkan kerugian di bank adalah fraud dalam bentuk skimming pada transaksi tariktunai ATM. Penelitian ini dilakukan untuk mengetahui pemodelan data mining yangdapat digunakan untuk mendeteksi fraud skimming di salah satu bank. Tujuan daripenelitian ini adalah memberikan referensi dalam mencari pemodelan deteksi fraud.Karakteristik data yang digunakan adalah imbalanced data karena data transaksi fraudsangat kecil dibandingkan dengan data transaksi normal. Metode yang digunakan padapenelitian ini adalah tinjauan pustaka, wawancara dan eksperimen terhadap teknikmachine learning. Pembentukan model pada penelitian ini dilakukan denganmengimplementasikan kombinasi dari penggunaan feature selection dan tanpa featureselection, penggunaan SMOTE dan tanpa SMOTE, serta penggunaan feature engineeringdan tanpa feature engineering dengan jarak dan jeda transaksi sehingga diperoleh delapanscenario dari hasil kombinasi. Hasil dari penelitian ini menunjukkan bahwa dari seluruhskenario yang diuji coba, algoritma Extreme Gradient Boosting merupakan algoritmaterbaik dalam menghasilkan model deteksi fraud. Skenario terbaik yang dihasilkan adalahskenario dengan mengimplementasikan ketiga teknik sekaligus yaitu feature selection,SMOTE dan feature engineering dengan jarak dan jeda transaksi. Berdasarkan hasilevaluasi model, pembentukan model dengan feature engineering dengan jarak dan jedatransaksi dapat meningkatkan performa model klasifikasi.

---

Bank is one of financial industry. As a financial industry that serve customers, bank is

potentially exposed to risk. One of potentially risk that making loss in bank is fraud in

form of skimming on ATM transaction. This study is conducted to know data mining

modelling that can be used to detect skimming fraud in a bank. The purpose of this study

is to provide reference in looking for fraud detection modelling. The characteristics of the

data used in this study is imbalanced data since fraud transaction data is very small

compared to normal transaction data. The method used in this study is the literature

review, semi-structured interviews, and experiments on machine learning techniques.

Creating model on this study is conducted by implementing combination of three used

techniques namely feature selection, SMOTE, and feature engineering with distance and

transaction lag. There are eight scenarios used in this study that were tested and analyzed

the results according to the needs of the case study research. The results of this study

indicate that the Extreme Gradient Boosting algorithm can identify fraudulent

transactions. The best scenario is a scenario by creating a model that implements feature

selection, SMOTE to handle imbalanced data, and feature engineering with distance and

transaction lag. Based on model evaluation, model generation by implementing feature

engineering with distance and transaction lag can improve performance of classification

model."

"Kerangka kerja konseptual mengenai praktik Audit Internal telah dikeluarkan oleh The Institute of Internal Auditor dimana Auditor Internal harus memiliki pengetahuan yang memadai untuk mengevaluasi risiko fraud dan cara organisasi mengelola risiko tersebut. Sehingga Audit Internal turut mempunyai peran dalam mencegah dan mendeteksi fraud. Walaupun pencegahan dan pendeteksian fraud merupakan tanggung jawab manajemen perusahaan, Auditor Internal diharapkan dapat melakukan dua hal tersebut sebagai bagian dari pelaksanaan tugas manajemen.Penelitian ini mengkaji penerapan program pencegahan dan pendeteksian fraud serta peran Audit Internal dalam mendukung efektivitas Fraud Management Program yang ada di perusahaan dengan metode penelitian kualitatif deskriptif dan pendekatan studi kasus. Observasi, wawancara dan studi dokumentasi digunakan dalam proses pengumpulan data.Hasil penelitian ini menjelaskan bahwa manajemen telah memiliki struktur pengendalian yang cukup baik dalam pencegahan dan pendeteksian fraud dan Audit Internal sudah berperan secara menyeluruh dalam semua komponen pembentuk effective Fraud Management Program.

---

Internal Audits Professional Practices Framework has been issued by The Institute of Internal Auditors, stated that Internal Auditors must have sufficient knowledge to evaluate the risk of fraud and the manner in which it is managed by the organization. Thus, Internal Audit also has a role in fraud prevention and detection. Although the responsibility in fraud prevention and detection addressed to the management, Internal Audit is expected to conduct those activities as part of the managements task force.

This study examines the application of fraud prevention and detection program and the role of Internal Audit in improving the effectiveness of Fraud Management Program in place by using qualitative descriptive research method and using case study approach. Observation, interview and documentation studies are used in data collection method.

As result explains that currently the management already has sufficient control structure in preventing and detecting fraud and Audit Internal has played a comprehensive role in all components that forming the effective Fraud Management Program."

"Skripsi ini bertujuan untuk menganalisis jenis-jenis kecurangan yang telah terjadi, bagaiamana penerapan program pencegahan dan pendeteksian kecurangan, serta peran audit internal dalam penerapan program pencegahan dan pendeteksian kecurangan pada PT. WXY. Ruang Lingkup penelitian ini terbatas pada cabang dan pabrik di PT. WXY. Penelitian ini menggunakan metode penelitian studi kasus dengan pendekatan kualitatif deskriptif. Data-data yang didapat merupakan hasil wawancara, dan kajian literatur yang kemudian di olah sesuai dengan tema penelitian. Berdasarkan analisis penelitian ini, dua kategori kecurangan yaitu korupsi dan penyalahgunaan aset berdasarkan Fraud Tree telah terjadi di PT. WXY. Manajemen memiliki kelemahan dalam struktur pengendalian internal dalam mencegah dan mendeteksi kecurangan. Namun, Audit Internal telah berperan dengan cukup baik dan aktif dalam penerapan program pencegahan dan pendeteksian kecurangan di perusahaan meskipun dengan batasan-batasan yang dimiliki.

---

This thesis aims to analyze the types of fraud that have occurred, how to implement fraud prevention and detection programs, as well as the role of internal audit in implementing fraud prevention and detection programs at PT. WXY. The scope of this research is limited to branches and factories at PT. WXY. This study uses a case study research method with a descriptive qualitative approach. The data obtained are the results of interviews and literature reviews which are then processed according to the research theme. Based on the analysis of this study, two categories of fraud, namely corruption and misappropriation of assets, based on the Fraud Tree have occurred at PT. WXY. Management has weaknesses in the internal control structure in preventing and detecting fraud. However, Internal Audit has played a fairly good and active role in implementing fraud prevention and detection programs in the company despite its limitations."

"[ABSTRAKPT Bank ABC Tbk sebagai salah satu bank yang bergerak di industri keuangan dituntut untuk menyesuaikan kebutuhan industri mengenai pengamanan transaksi kartu kredit. Bank Indonesia sebagai regulator mewajibkan setiap bank untuk mengimplementasikan PIN pada transaksi kartu kredit di Mesin EDC. Proses implementasi PIN memerlukan penyesuaian yang meliputi perubahan pada kartu, EDC dan back end system. Penyesuaian yang dilakukan berdampak pada proses bisnis kartu kredit hingga arsitektur teknologi yang digunakan. Pada penelitian ini digunakan framework TOGAF sebagai langkah kerja dalam memadukan proses bisnis organisasi, data dan arsitektur teknologi agar sesuai dengan standar dari EMVCo, PCI-DSS, Visa dan Mastercard. Hasil penelitian ini berupa solusi penyesuaian data, fitur serta alur pengembangan aplikasi yang dapat dijadukan acuan untuk perancangan standar arsitektur untuk implementasi PIN pada Transaksi Kartu Kredit.

---

ABSTRACTPT Bank ABC Tbk as one of the banks in the financial industry is required to match industry needs regarding security of the credit card transactions. Bank Indonesia as the regulator requires each bank to implement PIN on credit card transactions at EDC machine. PIN implementation process requires adjustments include changes to the card, the EDC and the back end system. Adjustments made an impact on the credit card business processes to architecture technology used. In this study used TOGAF framework as a step in the work to integrate the organization's business processes, data and technology architecture to match the standard of EMVCo, PCI-DSS, Visa and Mastercard. The results of this study is in the form of data matching solutions, application development features and workflow which can be used as standard reference for designing the architecture for the implementation of the PIN on Credit Card Transactions.;PT Bank ABC Tbk as one of the banks in the financial industry is required to match industry needs regarding security of the credit card transactions. Bank Indonesia as the regulator requires each bank to implement PIN on credit card transactions at EDC machine. PIN implementation process requires adjustments include changes to the card, the EDC and the back end system. Adjustments made an impact on the credit card business processes to architecture technology used. In this study used TOGAF framework as a step in the work to integrate the organization's business processes, data and technology architecture to match the standard of EMVCo, PCI-DSS, Visa and Mastercard. The results of this study is in the form of data matching solutions, application development features and workflow which can be used as standard reference for designing the architecture for the implementation of the PIN on Credit Card Transactions.;PT Bank ABC Tbk as one of the banks in the financial industry is required to match industry needs regarding security of the credit card transactions. Bank Indonesia as the regulator requires each bank to implement PIN on credit card transactions at EDC machine. PIN implementation process requires adjustments include changes to the card, the EDC and the back end system. Adjustments made an impact on the credit card business processes to architecture technology used. In this study used TOGAF framework as a step in the work to integrate the organization's business processes, data and technology architecture to match the standard of EMVCo, PCI-DSS, Visa and Mastercard. The results of this study is in the form of data matching solutions, application development features and workflow which can be used as standard reference for designing the architecture for the implementation of the PIN on Credit Card Transactions.;PT Bank ABC Tbk as one of the banks in the financial industry is required to match industry needs regarding security of the credit card transactions. Bank Indonesia as the regulator requires each bank to implement PIN on credit card transactions at EDC machine. PIN implementation process requires adjustments include changes to the card, the EDC and the back end system. Adjustments made an impact on the credit card business processes to architecture technology used. In this study used TOGAF framework as a step in the work to integrate the organization's business processes, data and technology architecture to match the standard of EMVCo, PCI-DSS, Visa and Mastercard. The results of this study is in the form of data matching solutions, application development features and workflow which can be used as standard reference for designing the architecture for the implementation of the PIN on Credit Card Transactions., PT Bank ABC Tbk as one of the banks in the financial industry is required to match industry needs regarding security of the credit card transactions. Bank Indonesia as the regulator requires each bank to implement PIN on credit card transactions at EDC machine. PIN implementation process requires adjustments include changes to the card, the EDC and the back end system. Adjustments made an impact on the credit card business processes to architecture technology used. In this study used TOGAF framework as a step in the work to integrate the organization's business processes, data and technology architecture to match the standard of EMVCo, PCI-DSS, Visa and Mastercard. The results of this study is in the form of data matching solutions, application development features and workflow which can be used as standard reference for designing the architecture for the implementation of the PIN on Credit Card Transactions.]"

"Penelitian ini bertujuan untuk melakukan identifikasi skema/skenario fraud yangberpotensi terjadi pada perusahaan dan memberikan usulan perbaikan atas risikoyang teridentifikasi dan rekomendasi strategi anti fraud yang sesuai denganperaturan OJK untuk meminimalkan terjadinya risiko fraud di dalam perusahaan.Pendekatan penelitian (research method) yang dilakukan bersifat studi kasus ataumetode kualitatif. Data yang diperoleh dalam penelitian yang dilakukan berasal darisumber data primer dan sumber data sekunder, yaitu dengan cara interview atauwawancara, observasi, serta studi dokumen atau document review. Hasil penelitianmenyimpulkan bahwa dari hasil fraud risk assessment atas proses bisnis,didapatkan ada 8 (delapan) skenario fraud yang dapat terjadi pada prosespenerimaan aplikasi kredit dengan risiko fraud yang harus ditindak lanjuti adalah88% dan 9 (sembilan) skenario fraud yang dapat terjadi pada proses penagihanpiutang dengan risiko fraud yang harus ditindaklanjuti sebesar 78%. Penelitimerekomendasikan usulan pengendalian internal atas skema/skenario fraud yangteridentifikasi dan telah menyusun strategi anti fraud dengan menggunakankerangka dari OJK yang telah disesuaikan dengan kondisi PT XYZ Finance.

---

This study aims to identify fraud schemes/scenarios that could potentially occur in

the company and provide recommendations for improvements to identified risks

and recommendations for anti-fraud strategies in accordance with OJK regulations

to minimize the risk of fraud within the company. The research approach (research

method) carried out is a case study or qualitative method. The data obtained in the

research carried out came from primary data sources and secondary data sources,

namely by means of interviews, observations, and document studies or document

reviews. The results of the study concluded that from the results of the fraud risk

assessment on business processes, there were 8 (eight) fraud scenarios that could

occur in the process of receiving credit applications with a risk of fraud that had to

be followed up by 88% and 9 (nine) fraud scenarios that could occur in the process

of collection of accounts receivable with a risk of fraud had to be followed up by

78%. Researcher recommends a proposal for internal control over identified fraud

schemes/scenarios and has developed an anti-fraud strategy using a framework

from the OJK that has been adjusted to the conditions of PT XYZ Finance"

"Kerentanan industri service terhadap keterjadian fraud, tidak efektifnya pengendalian internal dan terjadinya beberapa kasus fraud pada perusahaan, merupakan faktor utama yang mendorong peneliti untuk melakukan fraud risk assessment terutama pada proses bisnis procurement dan pengeluaran operasi. Tujuan dilakukannya fraud risk assessment ini adalah untuk menganalisis risiko fraud potensial, merekomendasikan pengendalian atas risiko tersebut dan merancang strategi anti fraud yang tepat bagi perusahaan, baik strategi preventif, detektif maupun investigatif. Jenis penelitian yang digunakan dalam penelitian ini adalah penelitian kualitatif dengan menggunakan pendekatan studi kasus. Sedangkan metode yang digunakan adalah single case with single unit analysis. Hasil penelitian menyimpulkan dari total 23 skenario fraud yang diidentifikasi 17 skenario proses bisnis procurement dan 6 skenario proses bisnis pengeluaran operasi , terdapat lima skenario yang memiliki tingkat risiko fraud residual paling tinggi high dan 3 skenario berada pada tingkat medium. Berdasarkan hasil penilaian ini, Peneliti memberikan rekomendasi pengendalian yang relevan untuk memitigasi risiko tersebut. Selain itu, Peneliti juga merekomendasikan strategi anti fraud yang relevan yang dapat diterapkan perusahaan untuk memitigasi keterjadian fraud. Strategi preventif yang direkomendasikan adalah pelaksanaan fraud risk awareness, code of conduct, tone of the top, pelaksanaan background check, membangun pengendalian internal yang baik dan membuat prosedur anti fraud. Sedangkan strategi detektif yang direkomendasikan adalah penerapan whistle blowing system, penerapan fraud risk indicator dan mystery shopping.

---

The vulnerability of the service industry to fraud incidence, ineffectiveness of internal controls and the occurrence of some cases of fraud to the company, is a major factor that encourages researchers to conduct fraud risk assessment, especially in procurement business processes and operating expenditure. The purpose of this research is to identify potential fraud risks, recommend control of these risks and suggest appropriate anti fraud strategies for the company, both preventive and detective strategies.

The type of research used in this research is qualitative by using case study approach. While the methodology used is single case with single unit analysis. The results of this study conclude that from the total 23 identified fraud scenarios 17 scenarios from business process procurement and 6 scenarios from operating expenditure , there are 5 scenarios with the highest residual fraud risk and 3 scenarios at medium level.

Based on the results of this assessment, the Researcher provides relevant control recommendations to mitigate such risks. In addition, researchers also recommend a relevant anti fraud strategy that can be applied to mitigate the company fraud incident. The recommended preventive strategy is the implementation of fraud risk awareness, code of conduct, tone of the top, implementation of background check, establishing good internal controls and making anti fraud procedures. While the recommended detective strategy is the application of whistle blowing system, application of fraud risk indicator and mystery shopping. "

"Dalam menjalankan bisnisnya, perusahaan telekomunikasi di sektor fixed broadband seringkali mengalami kebocoran pendapatan signifikan. Diantara beberapa penyebab kebocoran pendapatan, fraud merupakan faktor kebocoran yang memiliki dampak terbesar terhadap finansial dan citra perusahaan. Salah satu upaya untuk meminimalkan fraud dengan mendeteksi fraud yang dilakukan oleh pelanggan. Oleh karena itu, tujuan penelitian ini merancang classification model menggunakan machine learning untuk diaplikasikan terhadap sistem fraud detection. Classification model akan dibangun menggunakan supervised machine learning yang bertujuan untuk memprediksi kelas tertentu berdasarkan data historis yang didapatkan. Dalam penelitian ini, beberapa beberapa algoritme machine learning akan dibandingkan diantaranya logistic regression, decision tree, random forest, dan backpropagation neural network. Selain itu, dalam kasus fraud detection, data historis yang didapatkan memiliki perbandingan antar kelas yang tidak seimbang sehingga dibutuhkan pra-proses data balancing. Pada penelitian ini, data balancing dilakukan dengan oversampling berbasis Adaptive Synthetic (ADASYN). Hasil penelitian ini menunjukkan backpropagation neural network memiliki performa terbaik diantara algoritma lainnya. Selain itu didapatkan seluruh algoritme memiliki indikator performa diatas 90% menunjukkan pada kasus fraud detection di sektor fixed broadband, machine learning bekerja dengan akurat.

---

In running their business, telecommunications companies in the fixed broadband sector often experience significant revenue leakage. Among several causes of revenue leakage, fraud is the leakage factor that has the most significant impact on finances and corporate image. One of the efforts to minimize fraud is to detect fraud committed by customers. Therefore, this study aims to design a classification model using machine learning to be applied to the fraud detection system. The classification model will be built using supervised machine learning, which aims to predict certain classes based on historical data. Several machine learning algorithms will be compared in this study, including logistic regression, decision tree, random forest, and backpropagation neural network. In addition, in fraud detection, the historical data obtained has an unbalanced comparison between classes, so pre-processing data balancing is needed. In this research, data balancing is done by using Adaptive Synthetic (ADASYN) based oversampling. The results of this study indicate that the backpropagation neural network has the best performance among other algorithms. In addition, it is found that all algorithms have performance indicators above 90%, indicating that in the case of fraud detection in fixed broadband sector, machine learning works accurately."