Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : International Journal on Advanced Technology, Engineering, and Information System (IJATEIS)

SEMANTIC AND NATURAL LANGUAGE PROCESSING DEVELOPMENT APPLICATIONS FOR CHATBOTS TO ENHANCE ONLINE STORE CUSTOMER SERVICE Afandi, Yosi; Maskur, Maskur; Fiernaningsih, Nilawati; Fauzi, Ahmad
INTERNATIONAL JOURNAL ON ADVANCED TECHNOLOGY, ENGINEERING, AND INFORMATION SYSTEM Vol. 2 No. 4 (2023): NOVEMBER
Publisher : Transpublika Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55047/ijateis.v2i4.986

Abstract

Since customer support is time-limited, chatbot programs can assist potential online store visitors before they make a purchase. The general public cannot always answer inquiries or respond to customer requests. Virtual customer support allows potential customers to contact vendors regarding products they wish to purchase. This technology is very helpful in providing quick and accurate answers to various customer concerns and issues. The study focuses on the online retail environment where customer support is crucial for potential buyers before making a purchase. The Artificial Intelligence Markup Language (AIML) and Semantic Ontology were used by A.L.I.C.E. (Artificial Internet Linguistic Computer Agency) to develop an AI chatbot application. There are no online stores that use virtual customer service (chatbots) for customer support, so Batik Cloth, an application that offers batik textiles for sale in Malang, was chosen as the online store chatbot application for this study. Creating a chatbot with semantic capabilities involves using ontologies to process queries with more precise meaning. It achieves 92% accuracy for 15 types of relevant queries and responses, followed by 10 frequently asked questions as answers. Created by a potential buyer. Virtual customer support systems (chatbots) can respond to queries with similar terms or meanings by employing ontologies and semantics to deliver answers that fit the queries.
DESIGNING AN OMNICHANNEL MARKETING BUSINESS MODEL TO IMPROVE CUSTOMER EXPERIENCE Afandi, Yosi; Maskur, Maskur; Fiernaningsih, Nilawati; Herijanto, Pudji
INTERNATIONAL JOURNAL ON ADVANCED TECHNOLOGY, ENGINEERING, AND INFORMATION SYSTEM Vol. 3 No. 4 (2024): NOVEMBER
Publisher : Transpublika Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55047/ijateis.v3i4.1464

Abstract

System integration allows companies to bring together customer data from multiple channels, from websites to mobile apps and physical stores. Companies can have a more complete view of customer preferences and behavior, which in turn allows them to serve more relevant and personalized content to their customers. In an era where customers are inundated with information, content personalization is key to attracting customers' attention and maintaining their engagement. Furthermore, this business model emphasizes deep customer engagement across multiple channels. In an omnichannel environment, it is important for companies to stay connected with their customers no matter where they are. This can be achieved through responsive customer service, ongoing loyalty programs, and engaging content on social media and other online platforms. The results of this study discuss the analysis of application quality using five characteristics, namely Functional Suitability, Usability, Performance Efficiency, Portability and Compatibility. The results of the functional suitability characteristics of the omnichannel platform are said to be good. Usability gets 76.67% which means the omnichannel platform is called feasible. Performance efficiency of the website is good because the load process is less than 10 seconds. From these results it is concluded that the Omnichannel platform meets the predicate of satisfied. Compatibility of the Omnichannel platform did not find any location and performance problems on Edge, Chrome and Android browsers. The assessment results are expected to be recommendations and suggestions for developing an omnichannel platform to help the process of sending digital reminders that are better and more efficient.
Online Store Product Recommendation System Using Collaborative Filtering and Content-Based Filtering Algorithms to Increase Sales Afandi, Yosi; Maskur, Maskur; Widyananda, Wahyu; Fiernaningsih, Nilawati; Budiarti, Lina; Az Zuhri, Fahmi Muhammad
INTERNATIONAL JOURNAL ON ADVANCED TECHNOLOGY, ENGINEERING, AND INFORMATION SYSTEM Vol. 4 No. 3 (2025): AUGUST
Publisher : Transpublika Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55047/ijateis.v4i3.2007

Abstract

This study aims to evaluate and compare the performance of two recommendation system approaches, namely Collaborative Filtering (CF) and Content-Based Filtering (CBF), in providing relevant product recommendations to users in an e-commerce context. The dataset used consists of 120 data including 90 relevant and recommended products (True Positive), 20 recommended but irrelevant products (False Positive), and 10 relevant but not recommended products (False Negative). Based on the calculation results, both methods show a precision value of 0.818 and a recall of 0.900. This means that approximately 81.8% of products recommended by the system are truly relevant, while 90% of the total relevant products are successfully recommended to users. The F1-score value obtained of 0.857 illustrates a good balance between the accuracy and completeness of the recommendations generated by the system. Furthermore, to measure the level of rating prediction error, the Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) metrics are used. The evaluation results show that the CF method has an MSE value of 0.0784 and an RMSE of 0.28, while the CBF method shows an MSE of 0.0961 and an RMSE of 0.31. The lower RMSE value of CF indicates that this method has better accuracy in predicting user preferences than CBF. Overall, both methods show good performance with a low error rate. However, CF proved slightly superior in providing recommendations that match user preferences, so it can be used as a basis for developing smarter and more personalized recommendation systems on e-commerce platforms.