Article Per Year (5 Year)
p-Index From 2020 - 2025
1.817
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Bulletin of Electrical Engineering and Informatics International Journal of Supply Chain Management Journal of Saintech Transfer Indonesian Journal of Electrical Engineering and Computer Science Journal of Applied Data Sciences
Marischa Elveny, Marischa
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Transportation Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Managing Schema of Knowledge Acceleration Estimator (KAE) Model to Customer Behavior Using Business Metrics Syah, Rahmad; Nasution, M.K.M.; Elveny, Marischa; Nababan, Erna B; Sembiring, Sajadin
International Journal of Supply Chain Management Vol 9, No 5 (2020): International Journal of Supply Chain Management (IJSCM)
Publisher : ExcelingTech

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59160/ijscm.v9i5.4444

Abstract

Business metrics in Financial Technology 1500 users spread across North Sumatera Province. The impact of commercial digital business (commercial enterpreneurship and social entrepreneurship) is very large on users who are currently increasing in number. To produce Knowledge Acceleration (KAE) Model using Business Metrics on the impact of Commercial Entrepreneurship and Social Entrepreneurship in their utilization.Uncertainty arising from sustainable business operators by considering aspects of Business Metrics related. MARS an linear regression analysis method nonparametrics intended for statistics with the aim of facilitating research and modeling the relationships of each of the multi variables that arise
An boosting business intelligent to customer lifetime value with robust M-estimation Elveny, Marischa; Y. Syah, Rahmad B.; M. Nasution, Mahyuddin K.
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp1632-1639

Abstract

When a business concentrates too much on acquiring new clients rather than retaining old ones, mistakes are sometimes made. Each customer has a different value. Customer lifetime value (CLV) is a metric used to assess longterm customer value. Customer value is a key concern in any commercial endeavor. When there are variations in customer behavior, CLV forecasts the value of total customer income when the data distribution is not normal, and outliers are present. Robust M-estimation, a maximum likelihood type estimator, is used in this study to enhance CLV data. Through the minimization of the regression parameter from the residual value, robust Mestimation eliminates data outliers in customer metric data. With an accuracy of 94.15%, R-square is used to gauge model performance. This research shows that CLV optimization can be used as a marketing and sales strategy by companies.
An efficiency metaheuristic model to predicting customers churn in the business market with machine learning-based Y. Syah, Rahmad B.; Muliono, Rizki; Akbar Siregar, Muhammad; Elveny, Marischa
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp1547-1556

Abstract

Metaheuristics is an optimization method that improves and completes a task in a short period of time based on its objective function. The goal of metaheuristics is to search the search space for the best solution. Machine learning detects patterns in large amounts of data. Machine learning encourages enterprise automation in a variety of areas in order to improve predictive ability without requiring explicit programming to make decisions. The percentage of customers who leave the company or stop using the service is referred to as churn. The purpose of this research is to forecast customer churn in the market business. Particle swam optimization (PSO) was used in this study as a metaheuristic method to provide a strategy to guide the search process for new customers and obtain parameters for processing by support vector regression (SVR). SVR predicts the value of a continuous variable by determining the best decision line to find the best value. The number of transactions, the number of periods, and the conversion value are the parameters that are visible. Efficiency models are added to improve prediction results through two optimizations: prediction flexibility and risk minimization. The findings demonstrate the effectiveness of prediction in reducing customer churn.
A novel approach to optimizing customer profiles in relation to business metrics Elveny, Marischa; Nasution, Mahyuddin K. M.; Zarlis, Muhammad; Efendi, Syahril; Syah, Rahmad B. Y.
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i1.pp440-450

Abstract

Business is very closely related to customers. Each user owns the data, and the data is used to identify cross-selling opportunities for each customer. For example, the type of product or service purchased, the frequency of purchases, geographic location, and so on. By doing so, you can gain the ability to manage and analyze customer data, allowing you to create new opportunities in industries that were previously difficult to enter. The purpose of optimizing user profiles is to determine minimum or maximum business value and improve efficiency by determining user needs. In this study, multivariate adaptive regression spline (MARS) is a statistical model used to explain the relationship between the response variable and the predictor variable. Robust is used to find variable relationships to make predictions. To improve classification performance, the model is validated using a confusion matrix. The results show an accuracy value of 84.5%, with better time management (period management) reflected in the number of hours spent by merchants as well as discounts during that time period, which has a significant impact on any business. In addition, the distance between customers and merchants is also important, as customers prefer merchants who are closer to them to save time and transportation costs.
Complexity prediction model: a model for multi-object complexity in consideration to business uncertainty problems Syah, Rahmad B. Y.; Satria, Habib; Elveny, Marischa; K. M. Nasution, Mahyuddin
Bulletin of Electrical Engineering and Informatics Vol 12, No 6: December 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v12i6.5380

Abstract

In a competitive environment, the ability to rapidly and successfully scale up new business models is critical. However, research shows that many new business models fail. This research looks at hybrid methods for minimizing constraints and maximizing opportunities in large data sets by examining the multivariable that arise in user behavior. E-metric data is being used as assessment material. The analytical hierarchy process (AHP) is used in the multi-criteria decision making (MCDM) approach to identify problems, compile references, evaluate alternatives, and determine the best alternative. The multi-objectives genetic algorithm (MOGA) role analyzes and predicts data. The method is being implemented to expand the information base of the strategic planning process. This research examines business sustainability along two critical dimensions. First, consider the importance of economic, environmental, and social evaluation metrics. Second, the difficulty of gathering information will be used as a predictor for making long-term business decisions. The results show that by incorporating the complexity features of input optimization, uncertainty optimization, and output value optimization, the complexity prediction model (MPK) achieves an accuracy of 89%. So that it can be used to forecast future business needs by taking into account aspects of change and adaptive behavior toward the economy, environment, and social factors.
Differentiated learning with information technology for teachers at SMA Negeri 5 Padangsidimpuan Jaya, Ivan; Hardi, Sri Melvani; Elveny, Marischa
Journal of Saintech Transfer Vol. 7 No. 2 (2024): Journal of Saintech Transfer
Publisher : Talenta Publisher Universitas Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32734/jst.v7i2.14505

Abstract

Differentiated learning aims to improve classroom learning by accommodating students' diverse personalities and backgrounds, enabling effective and efficient participation. This community service provides training for teachers at SMA Negeri 5 Padangsidimpuan on differentiated learning methods using information technology through a blended learning approach. The training included pre- and post-tests to evaluate teachers' knowledge and skills. Results showed a significant improvement in teachers' ability to use interactive applications such as Padlet, Nearpod, Classcraft, and Kahoot, with post-test scores indicating an average increase of 20% compared to pre-test scores. Statistical analysis using the T-test confirmed the enhancement, with p-values below 0.05 for differentiated learning concepts and application usage. Teachers reported Kahoot as the most preferred application, followed by Padlet, Classcraft, and Nearpod. The study concludes that designing and implementing diverse instructional strategies using interactive media tailored to students' needs fosters meaningful learning experiences and improves teaching outcomes. Future efforts will include sustained support for teachers and the development of technology-focused learning modules.
Enhancing business analytics predictions with hybrid metaheuristic models: a multi-attribute optimization approach Syah, Rahmad B. Y.; Elveny, Marischa; Nasution, Mahyuddin K. M.
Indonesian Journal of Electrical Engineering and Computer Science Vol 38, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v38.i3.pp1830-1839

Abstract

This approach aims to optimize business analytical predictions through multiattribute optimization using a hybrid metaheuristic model based on the modified particle swarm optimization (MPSO) and gravitational search optimization (GSO) algorithms. This research uses a variety of data, such as revenue, expenses, and customer behavior, to improve predictive modeling and achieve superior results. MPSO, an interparticle collaborative mechanism, efficiently explores the search space, whereas GSO models’ gravitational interactions between particles to solve optimization problems. The integration of these two algorithms can improve the performance of business analytical predictions by increasing model precision and accuracy, as well as speeding up the optimization process. Model validation test results, precision 95.60%, recall 96.35%, accuracy 96.69%, and F1 score 96.11%. This research contributes to the development of more sophisticated and effective business analysis techniques to face the challenges of an increasingly complex business world.
An Effective Hybrid Approach for Predicting and Optimizing Business Complexity Metrics and Data Insights Syah, Rahmad B.Y; Elveny, Marischa; Ananda, Rana Fathinah; Nasution, Mahyuddin K.M; Hartono, Hartono
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.830

Abstract

This study proposes a hybrid approach for optimizing complexity prediction in the domain of business intelligence by integrating three powerful techniques: the Multi-Objective Complexity Prediction Model (MPK), Principal Component Analysis (PCA), and the XGBoost regression algorithm. The MPK model serves as a state-based simulator to capture system complexity dynamics, while PCA is employed to reduce data dimensionality and eliminate redundancy among features. Subsequently, XGBoost is used as a non-linear predictive model to estimate complexity values based on the refined input features. The results show that this hybrid approach significantly improves prediction accuracy, reduces data noise, and streamlines the modelling process. Quantitative evaluation using Mean Squared Error (MSE), Mean Absolute Error (MAE), and the R-squared (R²) metric demonstrates exceptional performance, with an MAE of 0.000035, an MSE of 6.7 × 10⁻⁹, and an R² of 0.9999999. These results confirm that the integration of MPK, PCA, and XGBoost is highly effective for complexity prediction tasks and can provide accurate and insightful outcomes in business intelligence analytics.
A novel MPK optimization framework for financial data analysis incorporating complexity and uncertainty management Syah, Rahmad Bayu; Elveny, Marischa; Ananda, Rana Fathinah; Nasution, Mahyuddin Khairuddin Matyuso
Bulletin of Electrical Engineering and Informatics Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i4.9358

Abstract

In a competitive environment, the ability to scale quickly and successfully is a critical need. This research proposes a new framework using multi-objective complexity prediction model (MPK) for financial data analysis, including complexity and uncertainty management. This model integrates input, uncertainty, and output optimization functions (OOFs) (input optimization function (IOF), uncertainty optimization function (UOF), and OOF) to predict complex output values under dynamic business conditions. Model evaluation is carried out using performance metrics, namely mean squared error (MSE), root mean squared error (RMSE), mean absolute error (MAE), and R² score. The evaluation results show that this model has an MSE value of 20.112, an RMSE of 2.267, and an MAE of 2.351, reflecting a low prediction error rate and high accuracy. In addition, the R² value of 0.884259 indicates that this model is able to explain around 88.4% of the variability in the output data, indicating its ability to capture complex data patterns. Thus, the proposed MPK model is effective in predicting output values in complex business scenarios and can be applied for strategic decision-making under conditions of uncertainty.
Enhancing marketing efficiency through data-driven customer segmentation with machine learning approaches Purnamasari, Fanindia; Putri Nasution, Umaya Ramadhani M. O.; Elveny, Marischa
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 2: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i2.pp1399-1410

Abstract

The importance of understanding consumer behavior in transaction data has become a key to improving marketing efficiency. This study aims to explore the application of machine learning (ML) techniques for data-driven consumer segmentation, focusing on improving product marketing strategies. This work addresses the limitations in the existing literature, especially in terms of handling high-dimensional data that can reduce segmentation quality. Previously, various studies have used clustering algorithms such as K-means without considering dimensionality reduction, which often leads to decreased accuracy and long computation time. In this study, we propose a new approach that combines principal component analysis (PCA) for dimensionality reduction and K-means clustering for consumer segmentation based on purchasing behavior. Experimental results show that using PCA to reduce data dimensionality significantly improves segmentation quality with an inertia score of 1,455,650 and a silhouette score of 0.486366. By implementing this method, we can group consumers into three segments based on frequently purchased product categories and the most common payment methods. These findings provide a scalable, data-driven segmentation framework that can be applied to improve marketing effectiveness by providing special discounts on various products based on the payment method used.
Co-Authors Akbar Siregar, Muhammad Ananda, Rana Fathinah Efendi, Syahril Habib Satria Hartono Hartono Jaya, Ivan Mahyuddin K. M Nasution Manurung, Dionikxon Marwan Ramli Muhammad Rivai Muhammad Zarlis, Muhammad Nababan, Erna B Nasution, M.K.M. Nasution, Mahyuddin K.M Purnamasari, Fanindia Putri Nasution, Umaya Ramadhani M. O. Rahmad Syah, Rahmad Rahman, Sayuti Rizki Muliono, Rizki Sajadin Sembiring Sri Melvani Hardi Syah, Rahmad B. Y. Syah, Rahmad B.Y Syah, Rahmad Bayu Y. Syah, Rahmad B.