Claim Missing Document
Check
Articles

Evaluating Explainable Artificial Intelligence Methods for Interpretable Machine Learning Models in Large Scale Enterprise Data Analytics Systems Indra Ava Dianta; Greget Widhiati; Andreas Tigor Oktaga
Big Data Analytics and Data Science Vol. 1 No. 1 (2026): March: Big Data Analytics and Data Science
Publisher : Asosiasi Pengelola Jurnal Informatika dan Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.66472/bdas.v1i1.19

Abstract

Explainable Artificial Intelligence (XAI) has become a critical area of research within artificial intelligence, focusing on improving the transparency and interpretability of machine learning (ML) models, often referred to as "black-box" models. The need for XAI techniques arises from the inherent complexity of ML models, which can make their decision-making processes difficult for users to understand. This study investigates various XAI techniques, including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to assess their impact on model interpretability without significantly compromising predictive performance. A comparative experimental design was used, applying these XAI methods to different ML models, including deep neural networks and ensemble methods, within large-scale enterprise data analytics systems. The results indicate that XAI methods significantly enhance model transparency and decision traceability, allowing users to understand the influence of individual features on predictions. While a slight reduction in predictive accuracy was observed, especially with simpler models, the trade-off between interpretability and performance was deemed acceptable, particularly in fields requiring transparency, such as healthcare, finance, and autonomous systems. The use of XAI in enterprise data systems has practical implications for fostering trust and enabling informed decision-making among stakeholders. Furthermore, the study discusses the challenges and limitations of applying XAI techniques, such as complexity, scalability, and model-specific limitations. Future research is suggested to focus on developing more scalable and efficient XAI methods, enhancing their applicability across various model types, and addressing the challenges of real-time applications. This will be crucial in ensuring the widespread adoption of XAI in critical domains, promoting the ethical use of AI while maintaining predictive accuracy.
Faktor-Faktor Penentu Keberhasilan UMKM di Era Digital: Pendekatan Pemodelan Prediktif Menggunakan Gradient Boosting Galuh Aditya; Siska Narulita; Agus Fitri Yanto; Andreas Tigor Oktaga
JURNAL MANAJEMEN DAN BISNIS EKONOMI Vol. 4 No. 3 (2026): Juli: JURNAL MANAJEMEN DAN BISNIS EKONOMI
Publisher : Institut Teknologi dan Bisnis (ITB) Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54066/jmbe-itb.v4i3.4180

Abstract

This study aims to compare the performance of three boosting algorithms, namely XGBoost, LightGBM, and CatBoost, to predict the success of MSMEs. The data used consists of 250 entries with 13 attributes that include business actor characteristics, initial capital, industry experience, financial record-keeping, internet utilization, business planning, partnerships, and the target variable success. The pre-processing stage includes checking for missing values, standardizing numerical attributes, and splitting the data into 80% training data and 20% test data. The evaluation results show that XGBoost provides the best performance with an accuracy of 0.92, precision of 0.8333, recall of 0.8333, F1-score of 0.8333, and ROC-AUC of 0.9715. LightGBM has an accuracy of 0.88, while CatBoost achieves an accuracy of 0.90. The research results show that XGBoost has the best ability to classify successful and unsuccessful MSMEs. The feature importance results also show that the success of MSMEs is influenced by a combination of several key factors. This research emphasizes that boosting algorithms are effectively used as predictive models to support the analysis of MSME success.
Green Entrepreneurship in Islamic Perspective: Building Sustainable Innovation Based on Ethical and Environmental Values Andreas Tigor Oktaga; Ahmad Dwi Nurdiyanto; Gulrukh Tukhlieva
Green Economics: International Journal of Islamic and Economic Education Vol. 1 No. 3 (2024): July: Green Economics: International Journal of Islamic and Economic Education
Publisher : International Forum of Researchers and Lecturers

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70062/greeneconomics.v1i3.422

Abstract

This research explores the integration of Islamic values into sustainable entrepreneurship, focusing on Muslim entrepreneurs who incorporate green innovation practices in their businesses. Despite growing awareness of sustainability, many Muslim entrepreneurs face challenges in aligning Islamic ethical principles with modern green business practices. This study aims to identify key Islamic values that guide sustainable entrepreneurship and analyze how faith-based motivations foster a culture of eco-conscious innovation. A qualitative descriptive research design, using a phenomenological approach, was employed to explore the experiences of Muslim entrepreneurs in environmentally sustainable sectors, including organic farming, renewable energy, and eco-friendly product manufacturing. Data was collected through semi-structured interviews, and thematic analysis was used to identify patterns of Islamic ethical influence on decision-making and innovation practices. The study found that Islamic entrepreneurship is rooted in values such as justice, stewardship, and social responsibility, which guide environmentally responsible innovation. These values encourage long-term sustainability, with a focus on community welfare and ecological preservation. The study also identified that Muslim entrepreneurs face barriers such as limited access to Sharia-compliant financing and financial literacy. The conclusions suggest promoting Sharia-based sustainable business frameworks, developing Islamic green financing instruments, and incorporating environmental education within Islamic entrepreneurship programs to foster more eco-conscious innovations. These findings offer valuable insights for policymakers, financial institutions, and entrepreneurs looking to integrate Islamic principles with sustainable development.
Pengaruh Iklan Meta Ads, Harga, dan Kualitas Produk Terhadap Minat Beli Online Produk Digital: Studi Kasus Instagram @Cuantanpakamera Kevin Boby Andika; RA Marlien; Andreas Tigor Oktaga
Prosiding Seminar Nasional Ilmu Manajemen Kewirausahaan dan Bisnis Vol. 2 No. 2 (2025): Desember : Prosiding Seminar Nasional Ilmu Manajemen Kewirausahaan dan Bisnis
Publisher : Asosiasi Riset Ilmu Manajemen Kewirausahaan dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/prosemnasimkb.v2i2.294

Abstract

This study aims to analyze the influence of Meta Ads, price, and product quality on the online purchase intention of digital products marketed through the Instagram account @cuantanpakamera. This study employs a quantitative approach. The population of this study consists of all 31,800 followers of the @cuantanpakamera Instagram account. The sampling technique used was purposive sampling, involving 125 respondents. Data analysis was conducted using multiple linear regression aided by the Statistical Package for Social Sciences (SPSS) 22.0 for Windows. The results indicate that Meta Ads, price, and product quality variables have a positive and significant effect on online purchase intention. Meta Ads was identified as the most dominant factor influencing online purchase intention. The coefficient of determination (R²) value of 0.663 indicates that the independent variables are able to explain 66.3% of the variation in online purchase intention, while the remaining 33.7% is explained by other factors such as consumer trust, brand awareness, and so forth. This study emphasizes the importance of implementing effective digital advertising strategies and consistent product quality management to enhance consumer purchase intention in the era of social media-based marketing.
Dampak FOMO Gen Z Kota Semarang dalam Keputusan Pembelian Produk Skincare di Aplikasi Tiktokshop Ilham Satya Hermawan; Andreas Tigor Oktaga
Jurnal Ekonomi, Bisnis dan Manajemen Vol. 5 No. 3 (2026): Jurnal Ekonomi, Bisnis dan Manajemen (EBISMEN)
Publisher : FEB Universitas Maritim Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/ebismen.v5i3.4757

Abstract

The rise of social commerce, particularly through the TikTok Shop platform, has revolutionized consumer purchasing behavior, especially concerning skincare products among the Gen-Z demographic. This investigation seeks to understand how content marketing, Influencer marketing, online customer reviews, and FOMO (Fear of Missing Out) affect skincare purchase decisions on TikTok Shop, simultaneously assessing FOMO's role as a mediating factor. A quantitative methodology was employed for this research, utilizing a Google Form survey distributed to 200 Generation Z participants residing in Semarang City, selected via a purposive sampling technique. Data analysis was conducted using Jamovi software, incorporating multiple linear regression and mediation analysis. The study's conclusions reveal that content marketing, online customer reviews, and FOMO exert a positive and significant influence on purchase decisions, whereas Influencer marketing does not show a significant direct effect. The developed model accounts for 74.9% of the variability in purchase decisions (R²=0.749). Mediation analysis validated FOMO's function as a mediator between the influence of both content marketing and Influencer marketing on purchase decisions, but not for the effect of online customer reviews. These outcomes indicate that purchase decisions are shaped by a simultaneous blend of informational and psycho-social routes.
Dampak Influencer sebagai Variabel Intervening bagi Pengguna TikTok Shop di Kota Semarang Cantik Padmasari; Andreas Tigor Oktaga
Profit: Jurnal Manajemen, Bisnis dan Akuntansi Vol. 5 No. 3 (2026): Agustus: Profit: Jurnal Manajemen, Bisnis dan Akuntansi
Publisher : UNIVERSITAS MARITIM AMNI SEMARANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58192/profit.v5i3.5000

Abstract

This study aims to analyze the Influencer of price and brand image on the purchase of fashion products among TikTok Shop users in Semarang City, both directly and through Influencers as a mediating variable. This study employed an ex-planatory quantitative approach. Data were collected through a closed-ended questionnaire distributed to 200 respondents selected using a purposive sampling technique. Data analysis was conducted through validity testing, reliability testing, classical assumption testing, regression analysis, and mediation analysis using Jamovi version 2.6.44. The results show that all research instruments met the criteria for validity and reliability. The Adjusted R-squared value of 0.604 in-dicates that price, brand image, and Influencers explain 60.4% of the variation in purchase decisions, while the remain ning 39.6% is explained by other factors outside the research model. Partially, price, brand image, and Influencers have a positive and significant effect on purchase decisions. In addition, Influencers are proven to partially mediate the influence of price and brand image on purchase decisions. These findings indicate that purchase decisions on TikTok Shop are not only determined by price considerations and brand image, but are also influenced by social validation and marketing com-munication built through Influencers.
Pengaruh Price, Brand Image, dan Electronic Word Of Mouth (E-Wom) terhadap Keputusan Pembelian Produk Thrift pada Konsumen Listiystore Listyani, Sari; Tigor Oktaga, Andreas
Jurnal Ilmiah Manajemen dan Kewirausahaan Vol. 5 No. 3 (2026): September: Jurnal Ilmiah Manajemen dan Kewirausahaan
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jimak.v5i3.8014

Abstract

 People's clothing choices currently do not rely entirely on new products, but have increasingly shifted towards wearable second-hand clothes (thrift) alongside the rapid development of digital businesses. Therefore, this study aims to examine the effect of price, brand image, and Electronic Word of Mouth (E-WOM) on the purchase decisions of thrift products among Listiystore consumers, both partially and simultaneously. To achieve this objective, the study utilizes a quantitative approach with a causal associative design. The accessible population includes 142 customers recorded in the Listiystore database in 2025. From this population, a sample of 105 respondents was drawn using the Slovin formula at a 5% margin of error through a simple random sampling technique. Furthermore, the Likert scale questionnaire responses were processed through multiple linear regression using IBM SPSS Statistics. The empirical testing results show that price, brand image, and E-WOM partially have a positive and significant effect on purchase decisions. In line with these findings, simultaneous testing also confirms that these three variables collectively exert a significant effect. Furthermore, the R Square value of 0.674 indicates that 67.4% of the variance in purchase decisions can be explained by the model, while the remaining 32.6% is influenced by other factors outside the scope of this study.
Perspektif Konsumen dan Dampaknya terhadap Minat Beli: Studi pada Geprek Mantul Semarang Faizah Mintya Rahmawati; Ahmad Dwi Nurdiyanto; Andreas Tigor Oktaga; Delta Lexi Arbawa
Jurnal Ilmu Manajemen, Ekonomi dan Kewirausahaan Vol. 6 No. 2 (2026): Juli : Jurnal Ilmu Manajemen, Ekonomi dan Kewirausahaan (JIMEK)
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jimek.v6i2.11142

Abstract

This study aims to analyze the influence of brand image, location, and servicescape on consumer purchase intention at Geprek Mantul, a restaurant operating in Mijen District, Semarang City. This study focuses on how consumer perspectives are formed and the most influential factors driving purchasing decisions in this growing local culinary business. In the context of increasingly competitive culinary industry, understanding consumer preferences and considerations is crucial for businesses to maintain and enhance competitiveness. The research method used was quantitative with a survey design approach. Primary data was obtained from 100 respondents, Geprek Mantul consumers, through an online questionnaire using a purposive sampling technique. Data analysis was conducted using multiple linear regression, supported by validity, reliability, F-tests, t-tests, and coefficients of determination to ensure model accuracy and the significance of each variable's influence. The results indicate that brand image, location, and servicescape have a positive and significant influence on consumer purchase intention, both partially and simultaneously. This finding confirms that these three variables are important aspects that consumers consider before deciding to make a purchase at Geprek Mantul, so that they can be the basis for developing a more effective marketing strategy.