Claim Missing Document
Check
Articles

Found 15 Documents
Search

FORECASTING HEALTH INSURANCE PAYER INCOME: A COMPARATIVE ANALYSIS OF DECISION TREE AND SVR ALGORITHMS Mokodaser, Wilsen Grivin; Soewignyo, Tonny Irianto; Tangka, George Morris William; Soewignyo, Fanny
Jurnal Riset Informatika Vol. 7 No. 3 (2025): Juni 2025
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2466.493 KB) | DOI: 10.34288/jri.v7i3.369

Abstract

An insurance company is a type of non-bank financial institution that protects clients from risks and collects premiums over a certain period, these facts provide an overview of the insurance business and highlight its role in the economy, this study evaluated the performance difference between the Decision Tree Regressor and Support Vector Regression (SVR) in predicting insurance payer income. The Decision Tree model demonstrated strong predictive accuracy, achieving a Mean Absolute Error (MAE) of approximately 57 million and an R-squared (R²) value of 0.896, meaning it could explain around 89.6% of the variance in the data. Additionally, the model maintained high consistency, as evidenced by 5-fold cross-validation scores ranging from 0.908 to 0.967, indicating strong generalization and low risk of overfitting. In contrast, the SVR model significantly underperformed. It recorded a much higher MAE of over 237 million and a large Mean Squared Error (MSE), reflecting substantial deviations from the actual values. Its R² score of -0.299 suggests that SVR performed worse than a naive mean predictor, failing to identify meaningful patterns. This poor performance was consistent across all cross-validation folds, which also produced negative R² scores. The SVR model’s inadequacy is likely due to the large scale of the income data and the lack of proper preprocessing, such as normalization, or parameter tuning. Overall, these findings clearly demonstrate that the Decision Tree Regressor is a more suitable, accurate, and stable model for predicting insurance payer income.
Tinjauan Literatur tentang Pengaruh Promosi, Kualitas Pelayanan, dan Ulasan Konsumen terhadap Keputusan Pembelian Online Soewignyo, Tonny; Ambalao, Shapely
YUME : Journal of Management Vol 8, No 3 (2025)
Publisher : Pascasarjana STIE Amkop Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37531/yum.v8i3.9857

Abstract

Penelitian ini bertujuan untuk melakukan tinjauan literatur komprehensif mengenai pengaruh promosi, kualitas pelayanan, dan ulasan konsumen terhadap keputusan pembelian online dalam konteks e-commerce di Indonesia. Perkembangan teknologi digital telah mengubah pola konsumsi masyarakat, menjadikan e-commerce pilihan utama karena efisiensi, kemudahan, dan kenyamanan. Oleh karena itu, pemahaman faktor-faktor yang memengaruhi keputusan pembelian konsumen menjadi krusial bagi perusahaan. Studi ini menggunakan metode kajian literatur dengan pendekatan deskriptif-kualitatif, menganalisis sepuluh artikel jurnal berbahasa Indonesia yang diterbitkan pada tahun 2024. Data dikumpulkan menggunakan perangkat lunak Publish or Perish yang terhubung ke Google Scholar, dengan kata kunci seperti "pengaruh promosi terhadap keputusan pembelian online", "kualitas pelayanan dalam e-commerce", dan "ulasan konsumen toko online". Hasil penelitian menunjukkan bahwa promosi memiliki dampak positif dan signifikan terhadap keputusan pembelian, meskipun efektivitasnya sangat bergantung pada konteks dan personalisasi. Kualitas pelayanan adalah faktor paling dominan dan konsisten dalam memengaruhi keputusan pembelian, meningkatkan loyalitas dan kepuasan pelanggan. Sementara itu, ulasan konsumen, atau electronic word of mouth, berperan penting sebagai referensi bagi calon pembeli, dengan sebagian besar studi menunjukkan pengaruh signifikan. Namun, pengaruh ulasan konsumen bersifat kontekstual dan kompleks, tidak selalu menjadi faktor utama jika kepercayaan merek sudah kuat. Secara keseluruhan, promosi, kualitas pelayanan, dan ulasan konsumen merupakan variabel penting yang memengaruhi keputusan pembelian online, namun dengan kekuatan pengaruh yang bervariasi. Kata Kunci: Promosi; Kualitas Pelayanan; Ulasan Konsumen; Keputusan Pembelian Online; E-commerce.
The Influence of Work Motivation and Work Discipline on Employee Performance Manado Independent School Soewignyo, Tonny; Paat, Silvia Friska; Kainde, Llly Linne; Mandagi, Deske Wenske; Petir, Abraham Leslie; Rantung, Rinny Cherryl
Syntax Literate Jurnal Ilmiah Indonesia
Publisher : Syntax Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36418/syntax-literate.v9i11.52375

Abstract

This research aims to investigate the influence of motivation and discipline on employee performance at Manado Independent School. Utilize quantitative research methods to determine whether motivation and discipline have an impact on employee performance. Primary data sources were used for this study. The data analysis method employed was multiple linear regression analysis conducted using SPSS 26 software. Data collection was carried out by distributing questionnaires to 100 respondents. Overall, the results of the multiple linear regression analysis and hypothesis testing suggest that motivation and discipline have a positive and significant influence when considered simultaneously, with a p-value of 0.000 < 0.05. The coefficient value is 1.87, and the adjusted R-squared value is 76.31%. Consequently, it can be concluded from this study that, partially, the variable of work motivation does not have a significant influence on employee performance, whereas the variable of work discipline has a significant impact on employee performance productivity. Therefore, efforts should be made to enhance work motivation to positively impact employee performance.
Exploring City Brand Gestalt Driver: The Case of Bitung City Mandagi, Deske W.; Darvel Civlie Walone; Tonny Irianto Soewignyo
Jurnal Ekonomi Vol. 13 No. 02 (2024): Jurnal Ekonomi, Edition April - June 2024
Publisher : SEAN Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

As urban landscapes evolve rapidly and competition among cities intensifies for economic growth and global recognition, the imperative to understand the dynamics of City Brand Gestalt (CBG) has heightened. This study aims to delve into the architecture of CBG by assessing the impact of its four dimensions (namely Story, Sensescape, Servicescape, and Stakeholder) on shaping Bitung City's overall brand gestalt. This research holds significance in formulating development strategies for CBG aimed at improving the economy of Bitung City, particularly in the tourism sector. A quantitative descriptive and causal research design was adopted by distributed and collected 250 self-administered online questionnaires from Bitung City visitors between January and May 2023. Structural Equation Modeling using SmartPLS was employed to determine the significant influence of each dimension on brand gestalt. The results confirmed the significant role of the 4S dimensions namely, story, sensescape, servicescape, and stakeholder in shaping the overall city brand gestalt.  In summary, this research underscores significant implications for city marketers and policymakers, emphasizing the necessity of crafting an appealing and positive brand narrative to enhance the image of a city. This, in turn, can bolster the city's economy, particularly in terms of tourism and other sectors.
Evaluasi Kinerja Algoritma Apriori dan FP-Growth untuk Association Rule Mining pada Data Transaksi Ritel Soewignyo, Fanny; Soewignyo, Tonny Irianto; Mokodaser, Wilsen Grivin; Silitonga, Argha Orion
Techno.Com Vol. 24 No. 4 (2025): November 2025
Publisher : LPPM Universitas Dian Nuswantoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62411/tc.v24i4.14952

Abstract

Ledakan data transaksi ritel yang terekam melalui sistem Point of Sale (POS) dan platform daring menuntut metode analisis yang efektif untuk menggali pola pembelian konsumen. Association Rule Mining merupakan pendekatan populer untuk menemukan keterkaitan antarproduk, dengan algoritma Apriori dan FP-Growth sebagai dua metode yang paling banyak digunakan. Penelitian ini bertujuan memberikan gambaran empiris mengenai efektivitas kedua algoritma tersebut pada data transaksi ritel yang nyata. Metode yang digunakan meliputi tahapan data understanding untuk mengenali struktur data, data cleaning untuk menghapus nilai kosong dan menyeragamkan format, serta data transformation menggunakan TransactionEncoder untuk mengubah data mentah menjadi format biner (one-hot encoded). Selanjutnya algoritma Apriori dan FP-Growth dijalankan dengan parameter yang sama untuk menghasilkan frequent itemsets dan aturan asosiasi. Evaluasi kinerja dilakukan dengan mengukur waktu pemrosesan, jumlah aturan yang dihasilkan, serta nilai support, confidence, dan lift tertinggi. Hasil penelitian menunjukkan bahwa kedua algoritma menghasilkan jumlah aturan yang sama (63 aturan) dengan support tertinggi 0,06, confidence tertinggi 0,51, dan lift tertinggi 3,29, tetapi waktu pemrosesan berbeda signifikan (Apriori 0,39 detik, FP-Growth 6,95 detik). Kesimpulannya, association rule mining efektif mengungkap pola pembelian konsumen, dan algoritma Apriori lebih efisien untuk dataset kecil hingga menengah, sedangkan FP-Growth lebih sesuai untuk dataset yang jauh lebih besar. Keywords - Association Rules, Apriori, FP-Growth, Frequent Itemset, Transaksi Ritel.