Hasil Pencarian  ::  Simpan CSV :: Kembali

"Learn the basics of Predictive analysis and data mining through an easy to understand conceptual framework and immediately practice the concepts learned using the open source RapidMiner tool. Whether you are brand new to Data Mining or working on your tenth project, this book will show you how to analyze data, uncover hidden patterns and relationships to aid important decisions and predictions. Data Mining has become an essential tool for any enterprise that collects, stores and processes data as part of its operations. This book is ideal for business users, data analysts, business analysts, business intelligence and data warehousing professionals and for anyone who wants to learn Data Mining.You’ll be able to :1. Gain the necessary knowledge of different data mining techniques, so that you can select the right technique for a given data problem and create a general purpose analytics process.2. Get up and running fast with more than two dozen commonly used powerful algorithms for predictive analytics using practical use cases.3. Implement a simple step-by-step process for predicting an outcome or discovering hidden relationships from the data using RapidMiner, an open source GUI based data mining tool."

"ABSTRAKSkripsi ini bertujuan untuk mengetahui kepuasan pelanggan layanan data operator CDMA di Indonesia dengan menggunakan pesan tweet sebagai data kepuasan pelanggan real time. Data tersebut diolah menggunakan text mining dan sentiment analysis dengan membuat model klasifikasi teks. Tingkat akurasi model yang dibuat untuk memprediksi sentimen dari pesan tweet mencapai 80 %. Hasil penelitian menunjukkan bahwa pelanggan data operator CDMA di Indonesia baik secara umum maupun pada masing-masing operator cenderung tidak puas dengan layanan data yang diberikan. Secara umum kriteria kemudahan koneksi paling mempengaruhi ketidakpuasan pelanggan layanan data operator CDMA di Indonesia. Sedangkan kriteria kemudahan koneksi paling mempengaruhi ketidakpuasan pelanggan layanan data operator CDMA 1. Kemudian kriteria kemudahan koneksi dan kehandalan jaringan paling mempengaruhi ketidakpuasan pelanggan layanan data operator CDMA 2.

---

ABSTRACTThis thesis aims to gain insight of customer satisfaction of Indonesian CDMA data services operators by using tweets as real time customer satisfaction data. The data is processed using text mining and sentiment analysis by creating text classification model. The model accuracy to predict sentiment of a tweet achieve 80%. The results showed that Indonesia CDMA data subcribers in general or to individual operators tend to not satisfied with the service provided. Connection easiness criteria most influencing customer dissatisfaction of Indonesia CDMA data service operators in general. While, the connection easiness criteria most influencing customer dissatisfaction of CDMA data service operator 1. Then, Connection easiness and network reliability criteria most influencing customer dissatisfaction of CDMA data service operator 2."

"Whether you are brand new to data mining or working on your tenth predictive analytics project, Commercial data mining will be there for you as an accessible reference outlining the entire process and related themes. In this book, you'll learn that your organization does not need a huge volume of data or a Fortune 500 budget to generate business using existing information assets. Expert author David Nettleton guides you through the process from beginning to end and covers everything from business objectives to data sources, and selection to analysis and predictive modeling.Commercial data mining includes case studies and practical examples from Nettleton's more than 20 years of commercial experience. Real-world cases covering customer loyalty, cross-selling, and audience prediction in industries including insurance, banking, and media illustrate the concepts and techniques explained throughout the book."

"This textbook presents a practical approach to predictive analytics for classroom learning. It focuses on using analytics to solve business problems and compares several different modeling techniques, all explained from examples using the SAS Enterprise Miner software. The authors demystify complex algorithms to show how they can be utilized and explained within the context of enhancing business opportunities. Each chapter includes an opening vignette that provides real-life example of how business analytics have been used in various aspects of organizations to solve issue or improve their results. A running case provides an example of a how to build and analyze a complex analytics model and utilize it to predict future outcomes."

"E-commerce dan big data merupakan bukti dari kemajuan teknologi yang sangat pesat. Big data berperan cukup penting dalam perusahaan e-commerce untuk menangani perkembangan semua data, mengolah setiap data tersebut dan menjadi competitive advantage bagi perusahaan. Perusahaan XYZ.com mengalami kesulitan dalam menganalisis stok dan tren dari produk yang dijual. Jika hal ini tidak ditanggulangi, maka perusahaan XYZ.com akan kehilangan opportunity gain. Untuk menentukan tren dan stok produk secara cepat dengan akurat, dibutuhkan big data predictive analysis. Penelitian ini mengolah data transaksi menjadi data yang dapat dianalisis untuk menentukan tren dan prediksi tren produk berdasarkan kategorinya dengan menggunakan big data predictive analysis. Hasil dari penelitian ini akan memberikan informasi kepada pihak manajemen kategori apa yang berpotensi menjadi tren dan jumlah minimal stok yang harus disediakan dari kategori produk tersebut.

---

E commerce and big data are evidence of rapid technological advances. Big data plays an important role in e commerce companies to handle and analyze all data changes, and become a competitive advantage for the company. XYZ.com experience a difficulty in analyzing stocks and commerce product trend. If this issue not addressed, XYZ.com company will lose an opportunity gain. To determine trends and stock accurately, XYZ.com can use big data predictive analysis. This study processes transaction data into data that can be analyzed to determine trends and predictions of product trends based on its categories using big data predictive analysis. The results of this study give massive informations to management about what categories will potential become trends and minimum stock required to be provided."

"Whether you are brand new to data mining or working on your tenth predictive analytics project, Commercial Data Mining will be there for you as an accessible reference outlining the entire process and related themes. In this book, you'll learn that your organization does not need a huge volume of data or a Fortune 500 budget to generate business using existing information assets. Expert author David Nettleton guides you through the process from beginning to end and covers everything from business objectives to data sources, and selection to analysis and predictive modeling."

"

Sistem e-procurement merupakan sistem pengadaan yang dilakukan dengan cara elektronik yang menjadi faktor kunci untuk mengelola keuangan negara dengan kontrol yang tepat, serta dilindungi oleh kebijakan dan peraturan perundang-undangan yang berlaku. Menurut Asian Development Bank e-tendering, yang merupakan bagian dari e-procurement, merupakan aplikasi strategis yang dapat menunjang kinerja pada sektor pemerintahan. Berdasarkan temuan praktik yang tidak sesuai dengan prinsip pengadaan, maka dalam penelitian ini dilakukan sebuah analisis mendalam untuk mengevaluasi kegiatan tender pada lembaga kementerian di Indonesia. Pada penelitian ini ditunjukkan bagaimana penambangan data dilakukan pada portal pengadaan nasional untuk menganalisis data tender dan mendapatkan temuan pola tersembunyi yang berguna untuk pengambilan keputusan. Penelitian ini menggunakan metodologi web data mining dengan melakukan pendekatan analisis secara deskriptif dan statistik. Dengan melakukan metode uji chi-square dan multivariance Anova, ditemukan adanya kaitan antara lembaga kementerian dengan pemenang berulang pada tahun anggaran 2018-2019. Di samping itu frekuensi partisipasi peserta tidak memiliki dampak terhadap statistik kemenangan berulang pada Kementerian Perhubungan, tetapi berdampak pada Kementerian PUPR. Penelitian ini juga menemukan adanya hubungan yang sangat kuat antara variabel Harga Perkiraan Sendiri (HPS) dengan nilai pagu. Selain itu pada penelitian ini juga ditemukan anomali data pada harga penawaran pemenang tender dengan nilai 100 kali lebih besar dari harga pagu dan HPS.

 

---

E-procurement is an electronic procurement system that became a key factor required to manage financial aspect of a country with appropriate controls, and protected by legal policies. According to Asian Development Bank, e-tendering as part of e-procurement, is classified as a strategic application that can enhance performance in the government sector. Based on the finding of practices that are not comply with the principles of good procurement governance, in this study an in-depth analysis was conducted to evaluate the tender activities of the ministry in Indonesia. This research shows how data mining is carried out at the national procurement portal to analyze tender data and findings the hidden pattern that would be useful for decision making. This study uses a web data mining methodology by conducting a descriptive and statistical analysis approach. By using the chi-square and multivariance Anova test method, this study has found that there was a relation between the ministries and repeated winners in year 2018-2019. In addition, the frequency of participation did not have an impact on the statistics of recurring wins at the Ministry of Transportation, but it had an impact on the Ministry of Public Works and Public Housing. This study also found a very strong relationship between the Owner Estimate (OE) value and the threshold value. In addition on this study, it was found anomaly data on the tender bid price of the winner with a value 100 times greater than the threshold value and OE value.

"

"Perusahaan XYZ menerapkan Customer Life Cycle atau CLC yang sudah disesuaikan dengan kebutuhan perusahaan demi menjaga loyalitas pengguna. Tak hanya menjaga loyalitas, Perusahaan XYZ menerapkan CLC guna memperluas bisnis yang dijalani olehnya. Dengan bantuan teknologi, CLC dapat dengan mudah untuk dianalisis lebih mendalam. Teknologi yang digunakan berupa pembelajaran mesin. Pembelajaran mesin ini diimplementasikan untuk mendapatkan insight dari data yang dimiliki Perusahaan XYZ. Dalam mendapatkan insight tersebut, digunakan beberapa metode seperti Support Vector Machine, Logistic Regression, Gradient Boosting, Random Forest, Decision Tree, dan FPGrowth. Insight yang didapatkan selanjutnya ditampilkan dalam bentuk visualisasi data yang diaplikasikan ke dalam website. Terdapat tiga permasalahan berbeda yaitu prediksi pembeli potensial, prediksi produk yang akan dibeli, dan prediksi waktu pembelian berikutnya. Permasalahan pertama dapat diselesaikan dengan model Logistic Regression dengan f1-score sebesar 76.35%. Permasalahan kedua diselesaikan dengan model FP-Growth dengan nilai minimum support dan confidence sebesar 0.001. Untuk permasalahan ketiga dapat diselesaikan dengan model Decision Tree dengan nilai akurasi 78.76% dan f1-score sebesar 77.01%. Dilakukan pula pengujian terhadap response time serta SQL query yang digunakan pada setiap endpoint yang bekerja sebagai aktor untuk melakukan distribusi data kepada aplikasi frontend dan aktor untuk melakukan update database. Terakhir, dilakukan pula pengujian terhadap visualisasi data. Pengujian terhadap visualisasi data dilakukan secara kualitatif. Pengujian ini dilakukan dengan menerapkan beberapa tipe visualisasi data untuk tiap business question yang ada. Setelah itu, dilakukan perbandingan pada tiap tipe visualisasi data sehingga mendapatkan visualisasi data yang tepat untuk tiap business question yang ada.

---

XYZ Company implements customized Customer Life Cycle or CLC that fits with company’s needs in order to maintain user loyalty. Not only maintaining user loyalty, XYZ Company implements CLC in order to expand its business. With the help of technology, CLC can be easily analyzed with more depth. Technology that is being used within this research is machine learning. Machine learning is implemented to gain insights from data owned by Company XYZ. While obtaining insights, machine learning use several various methods such as Support Vector Machine, Logistic Regression, Gradient Boosting, Random Forests, and Decision Trees. The insights obtained from machine learning are displayed in the form of data visualization that is applied to website. Examination on the machine learning model was formed with different data balancing techniques. Examination using Undersampling balancing technique along with Decision Tree model gives the highest f1-score value at 88.70%. Examination were also conducted on the response time and SQL queries were also carried out for each endpoint that works as an actor to distribute data to frontend applications and actors to update the database. Finally, examination and comparison is conducted on data visualization using qualitative approach. Moreover, this examination is conducted by applying several types of data visualization for each existing business questions. At the end, comparisons were made for each type of data visualization to get the optimum visualization regarding each business question."