Claim Missing Document
Check
Articles

Found 32 Documents
Search

Kodein-Penetration: Recommendations of Customer Personalization Level in A CRM using Deep Learning Sudianto Sudianto; Muhammad Lulu Latif Usman; Dedy Agung Prabowo; Muhamad Azrino Gustalika; Silvia Van Marsally; Fajar Kamaludin Akhmad; Nazwa Aulia Rakhma; Bunga Laelatul Muna; Apri Pandu Wicaksono; Ari Rachman
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.597

Abstract

This study aims to develop a personalization-level recommendation model implemented in the Customer Relationship Management (CRM) system at PT Kodegiri, called KodeinPenetration. Personalization in CRM aims to improve customer interaction by providing more relevant recommendations based on their needs and preferences. To achieve this goal, this study tested several classification models using historical customer interaction data as the basis for analysis. The classification models tested included decision tree-based methods such as Random Forest, Gradient Boosting, and AdaBoosting, as well as deep learning models such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). In addition, two main feature extraction techniques were applied to process text data, namely TF-IDF (Term Frequency-Inverse Document Frequency) and Tokenizer Padding. TF-IDF is used to represent words as numeric vectors based on their frequency of occurrence. In contrast, Tokenizer Padding is used in deep learning models to convert text into a numeric format that neural networks can process. The test results showed that the decision tree-based method using the TF-IDF feature produced the best accuracy of up to 82%. On the other hand, the deep learning model with GRU architecture utilizing Tokenizer Padding achieved the highest accuracy of 88.23%. This shows that the deep learning model has greater potential in handling sequential data and providing more accurate results compared to traditional methods. This study provides an important contribution to the development of deep learning-based personalized recommendation systems in CRM. By leveraging historical customer interactions, this system can improve user experience by offering more relevant and targeted services.
SiAkif-Bots: Gemini AI for Academic Service Chatbots Bunga Laelatul Muna; Sudianto Sudianto; Muhammad Lulu Latif Usman
Journal of Applied Engineering and Technological Science (JAETS) Vol. 6 No. 2 (2025): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v6i2.6728

Abstract

Academic services are an important element in education, as they provide students with access to information and support. At Telkom University Purwokerto, there are obstacles to the efficiency of academic services, especially due to information delays and the high burden of onsite services. To overcome this challenge, a Telegram-based chatbot, "SiAkif," was developed using the Large Language Model (LLM) model from Gemini AI. Gemini AI's selection is based on its ability to understand complex conversational contexts and generate accurate and relevant responses. This research aims to implement the Telegram chatbot that utilizes Gemini AI for Indonesian-language academic services. The implementation showed satisfactory results, with the chatbot "SiAkif" recording an average BLEU score of 0.88, which reflects good performance and response. This chatbot effectively reduces information delays, expands service accessibility, and improves student experience in interacting with institutions. Through "SiAkif," the institution is expected to strengthen the interaction between students and academic services, making it a potential solution for digital transformation in education.