In today's highly competitive business landscape, companies face a significant challenge in making accurate decisions based on vast amounts of historical data. Reliance on human data analysis often leads to biases and errors, hindering the ability to extract effective insights for sales forecasting. To address this challenge, this research presents an advanced model that integrates 14 machine learning (ML) regression algorithms, including XGBRegressor and LGBMRegressor, to provide accurate sales predictions using a comprehensive global store dataset. The results demonstrate that XGBRegressor and LGBMRegressor achieved the highest test accuracy (92%) and the lowest error rates, proving their ability to handle complex prediction tasks efficiently. This high accuracy in sales forecasting enables companies to make more effective strategic decisions, such as optimizing inventory management, allocating resources optimally, and exploring new growth opportunities. Consequently, the use of these advanced algorithms directly contributes to increasing sales volume and achieving a sustainable competitive advantage.
With technological developments that are increasingly significant every year, many organizations or companies are led to change activities digitally without exception for student organizations that are required to do the same thing.Student organizations have the meaning of an organization that is formally and officially registered under the university.Other than that, it is not included in the context of student organizations.However, the implementation of digital transformation encountered many obstacles, such as a lack of prepared human resources, lack of support, and the reluctance to make significant changes.The method used in this research qualitatively uses a literature review method.The results of this research propose implementation steps that can be applied to student organizations, solutions to challenges during implementation, and a new factor in the digital organization, namely the digital mindset.
The use of chatbots nowadays is expanding in some fields in human life.It has been used in customer service, education, etc.In the educational area, a chatbot has been used to help students to learn, or to give information relates to the academic and non-academic area, it even helped students to choose the elective course for the next semester.Even though it has been used for many purposes, not all education institutions implement the chatbot.Seeing that challenge, in this paper, the researchers try to develop a chatbot to improve students' academic service in one of the study programs in Bina Nusantara University, namely Information Systems.The researchers want to give more improvement in the way students communicate with the department, whereas now it's only through social media like Facebook, Instagram, and Line.The methods for analysis and development of this chatbot use the foundation of Decision Support Systems (DSS).Other methods for collecting data are also being used to develop the flow of the Chatbot that is through the questionnaire and interview with some of the stakeholders.The result of the research is the chatbot flow that can be used as the first step to develop a chatbot.
A cryptocurrency exchange application is a platform that provides a facility for users to do a crypto asset transaction. In Indonesia, there are two types of applications, regulated and unregulated apps with various and different facilities. This research aims to analyze factors that influence users' acceptance to use cryptocurrency exchange applications with extended TAM methods with 7 external variables such as design, experience, perceived risk, regulatory support, social influence, trust, and perceived benefit. Then, we analyzed the data collected using the Structural Equation Modeling (SEM) - Partial Least Square (PLS) method. This research's result was conducted to analyze and give recommendations for the next research and the apps provider regarding factors that influenced users’ acceptance to use the cryptocurrency exchange application. The number of samples will be determined using a formula from Roscoe Theory with a minimum of 110 respondents and the questionnaire was filled out by 130 respondents using Google forms. This research's result has proven that trust and design are external variables that affect cryptocurrency exchange application acceptance. In contrast with the previous study in which regulatory support affects the user's trust, this research found social influence and experience are variables that affect user's trust (Albayati et al., 2020).
