scholarly journals Sistem Rekomendasi Produk Pena Eksklusif Menggunakan Metode Content-Based Filtering dan TF-IDF

Author(s):  
Mariani Widia Putri ◽  
Achmad Muchayan ◽  
Made Kamisutara

Sistem rekomendasi saat ini sedang menjadi tren. Kebiasaan masyarakat yang saat ini lebih mengandalkan transaksi secara online dengan berbagai alasan pribadi. Sistem rekomendasi menawarkan cara yang lebih mudah dan cepat sehingga pengguna tidak perlu meluangkan waktu terlalu banyak untuk menemukan barang yang diinginkan. Persaingan antar pelaku bisnis pun berubah sehingga harus mengubah pendekatan agar bisa menjangkau calon pelanggan. Oleh karena itu dibutuhkan sebuah sistem yang dapat menunjang hal tersebut. Maka dalam penelitian ini, penulis membangun sistem rekomendasi produk menggunakan metode Content-Based Filtering dan Term Frequency Inverse Document Frequency (TF-IDF) dari model Information Retrieval (IR). Untuk memperoleh hasil yang efisien dan sesuai dengan kebutuhan solusi dalam meningkatkan Customer Relationship Management (CRM). Sistem rekomendasi dibangun dan diterapkan sebagai solusi agar dapat meningkatkan brand awareness pelanggan dan meminimalisir terjadinya gagal transaksi di karenakan kurang nya informasi yang dapat disampaikan secara langsung atau offline. Data yang digunakan terdiri dari 258 kode produk produk yang yang masing-masing memiliki delapan kategori dan 33 kata kunci pembentuk sesuai dengan product knowledge perusahaan. Hasil perhitungan TF-IDF menunjukkan nilai bobot 13,854 saat menampilkan rekomendasi produk terbaik pertama, dan memiliki keakuratan sebesar 96,5% dalam memberikan rekomendasi pena.

2021 ◽  
Vol 2 (1) ◽  
pp. 19-26
Author(s):  
Didit Rahadi Wicaksono

Atria Hotel Malang adalah salah satu hotel bintang empat yang terletak di Kota Malang, tepatnya berada di jantung kota Malang. Pihak manajemen hotel perlu menerapkan strategi pemasaran berupa Customer Relationship Management (CRM) untuk menciptakan kepuasan pelanggan terhadap pelayanan yang diberikan. Dalam melaksanakan strategi CRM, ada empat implementasi untuk menciptakan dan mengelola hubungan dengan pelanggan, yaitu: (1) identifikasi; (2) diferensiasi; (3) interaksi; (4) Customize. Metode penelitian yang digunakan peneliti adalah metode penelitian kualitatif. Berdasarkan hasil penelitian dapat disimpulkan bahwa Implementasi Customer Relationship Management (CRM) pada sales and marketing department dalam memelihara dan menjaga hubungan baik dengan pelanggan sudah dilaksanakan dengan baik dalam pengembangan brand awareness kepada publik, namun dalam penerapan customer relationship management masih belum dilakukan secara efektif karena masih terdapat banyak database pelanggan pada corporate segment yang menumpuk dan tidak valid lagi akibat dari pengelolaan hubungan yang tidak merata kepada pelanggan. Atria Hotel Malang memerlukan ide yang kreatif dan inovatif di setiap tahunnya agar mampu meningkatkan kualitas produk dan citra perusahaan di hadapan konsumen.


2019 ◽  
Vol 8 (3) ◽  
Author(s):  
Magma Zulfiqar Ismail ◽  
Sulhaini Sulhaini ◽  
Handry Sudiartha Athar

This study aims to determine the effect of Customer Relationship Management on Product Knowledge and Customer Loyalty Intention PT. Bank BNI Syariah Mataram Branch. And to find out the effect of Product Knowledge on Customer Loyalty Intention, PT. Bank BNI Syariah Mataram Branch. The type of research used is causality with a non purposive sampling technique. The population in this study is the customer of PT. Bank BNI Syariah Mataram Branch in the past year amounted to 100 respondents with data collection techniques using questionnaires. Data analysis uses path analysis with the help of Structural Equation Modeling (SEM) with AMOS Software.The results of the study show that; Customers Relationship Management (CRM) has a positive and significant effect on Product Knowledge at the BNI BNI Syariah Bank Branch. Product Knowledge has a positive and significant influence on consumer Loyalty Intention at the BNI BNI Syariah Bank Branch. Customers Relationship Management (CRM) has a positive and significant influence on consumer Loyalty Intention at the BNI BNI Syariah Bank Branch.Keywords : Customers Relationship Management (CRM), Product Knowledge dan Loyalty Intention


Author(s):  
Calin Gurau

Electronic commerce requires the redefinition of the firm’s relationships with partners, suppliers, and customers. The goal of effective customer relationship management (CRM) practice is to increase the firm’s customer equity, which is defined by the quality, quantity, and duration of customer relationships (Fjermestad & Romano, 2003). The explosive development of the online market and the rapid evolution of customer management applications have determined the companies to implement electronic customer relationship management (eCRM) systems, which are using advanced technology to enhance customer relationship management practices. The successful implementation of an eCRM system requires a specific combination of IT applications that support the classic domains of the CRM concept: marketing, sales, and service (Kennedy, 2006). Electronic marketing aims for acquiring new customers and moving existing customers to further purchases. Electronic sales try to simplify the buying process and to provide superior customer support. Electronic service has the task to provide electronic information and services for arising questions and problems or to convey customers to the right contact person in the organization. The eCRM system comprises a number of business processes, interlinked in a logical succession: • Market segmentation: The collection of historical data, complemented with information provided by third parties (such as marketing research agencies), is segmented on the basis of customer life-time value (CLV) criteria, using data mining applications. • Capturing the customer: The potential customer is attracted to the Web site of the firm through targeted promotional messages, diffused through various communication channels. • Customer information retrieval: The information retrieval process can be either implicit or explicit. When implicit, the information retrieval process registers the Web behaviour of customers, using specialized software applications, such as “cookies.” On the other hand, explicit information can be gathered through direct input of demographic data by the customer (using online registration forms or questionnaires). Often, these two categories of information are connected at database level. • Customer profile definition: The customer information collected is analyzed in relation with the target market segments identified through data mining, and a particular customer profile is defined. The profile can be enriched with additional data (e.g., external information from marketing information providers). This combination creates a holistic view of the customer, his needs, wants, interests and behaviour (Pan & Lee, 2003). • Personalization of firm-customer interaction: the customer profile is used to identify the best customer management campaign (CMC), which is applied to personalize the company-customer online interaction. • Resource management: The company-customer transaction require complex resource management operations, which are partially managed automatically, through specialized IT-applications, such as Enterprise Resource Planning (ERP) or Supply Chain Management (SCM), and partly through the direct involvement and coordination of operational managers.


2019 ◽  
Author(s):  
Matthew J. Lavin

This lesson focuses on a foundational natural language processing and information retrieval method called Term Frequency - Inverse Document Frequency (tf-idf). This lesson explores the foundations of tf-idf, and will also introduce you to some of the questions and concepts of computationally oriented text analysis.


2021 ◽  
Vol 8 (2) ◽  
pp. 207
Author(s):  
I Putu Gede Hendra Suputra ◽  
Kiki Dwi Prebiana ◽  
Frisca Olivia Gorianto

Pada sebuah sistem temu kembali,salah satu cara untuk mencari kesamaan antara query dengan dokumen adalah dengan menggunakan Term Frequency – Inverse Document Frequency atau TF-IDF. TF yang umum digunakan adalah langsung menggunakan jumlah term frequency padahal banyak jenis TF lainnya yang dapat dikombinasikan dengan IDF. Penelitian ini akan mengkombinasikan 4 jenis TF, yaitu Natural TF, Normalization/max TF, Logaritma TF, dan Boolean TF dengan tujuan untuk mencari jenis TF mana yang lebih baik setelah dikombinasikan dengan IDF. Hasil penelitian menunjukkan bahwa.Logaritma TF adalah yang terbaik dengan nilai F-measure sebesar 0,00662. Keywords: TF-IDF, Natural TF, Normalization TF, Logaritma TF, Boolean TF


Author(s):  
Didit Suhartono ◽  
Khodirun Khodirun

The archive is one of the examples of documents that important. Archives are stored systematically with a view to helping and simplifying the storage and retrieval of the archive. In the information retrieval (Information retrieval) the process of retrieving relevant documents and not retrieving documents that are not relevant. To retrieve the relevant documents, a method is needed. Using the Term Frequency-Inverse Document and Vector Space Model methods can find relevant documents according to the level of closeness or similarity, in addition to applying the Nazief-Adriani stemming algorithm can improve information retrieval performance by transforming words in a document or text to the basic word form. then the system indexes the document to simplify and speed up the search process. Relevance is determined by calculating the similarity values between existing documents by querying and represented in certain forms. The documents obtained, then the system sort by the level of relevance to the query.


2014 ◽  
Vol 651-653 ◽  
pp. 2258-2261 ◽  
Author(s):  
Dong Dong Xu ◽  
Shao Bo Wu

Term frequency/inverse document frequency (TF-IDF) is widely used in text classification at present, which is borrowed from Information Retrieval. Based on this conventional classical TF-IDF formula, we present a new TF-IDF weight schemes named CTF-IDF. The experiment shows that the improved method is feasible and effective. Furthermore, from the subsequent evaluations using 10-fold cross-validation, we can see the CTF-IDF greatly improves the accuracy of text classification.


2018 ◽  
Vol 7 (2) ◽  
pp. 180
Author(s):  
Wiyanto Wiyanto ◽  
Fajar Butsianto ◽  
Karsito Karsito

Information technology is rapidly developed in this century that impact to various aspects of the organization really need information technology to support the performance and everyday business processes. In health services, information technology is required to process and storage the patient medical records, so that the patient's medical record is well preserved, and competitive advantage can be obtained between patient and polyclinic. The application of Customer Relationship Management (CRM) approach can be developed by implementing information system of medical record history to get new patient and retain existing patient, improving relationship with patient and maintaining patient loyalty as well as supporting the company/organization to provide excellent service to customers in real time through the advantage of information technology. The aims of this research are to understand patient medical record by CRM approach and Unified Modeling Language (UML) for system design, system validation using Forum Group Discussion (FGD), and using software testing Model ISO 9126. The result of this research are Medical Record History Information System and the result of system validation with FGD is 100% accepted, the result of system test using Model ISO 9126 is good with success rate 82,86%, so it can give contribution to polyclinic.


2001 ◽  
Vol 30 (8) ◽  
pp. 417-422 ◽  
Author(s):  
Hajo Hippner ◽  
Stephan Martin ◽  
Klaus D. Wilde

Sign in / Sign up

Export Citation Format

Share Document