Aplikasi web interaktif untuk pembelajaran anak usia dini tentang pengenalan hewan merupakan alat edukatif yang penting, dirancang untuk membantu anak-anak mengenali berbagai jenis hewan melalui gambar dan deskripsi hewan yang disediakan. Model Convolutional Neural Network (CNN) digunakan untuk mengklasifikasikan gambar hewan yang diunggah oleh pengguna. Metode yang digunakan melibatkan pengolahan gambar menggunakan CNN untuk mengidentifikasi jenis hewan berdasarkan gambar yang diberikan, kemudian hasil identifikasi ditampilkan dalam antarmuka web yang interaktif. Hasil pengujian menunjukkan bahwa model CNN mencapai akurasi sebesar 59.93% dan presisi sebesar 59.92%. Namun, model mengalami masalah overfitting, yang terlihat dari performa yang lebih tinggi pada data pelatihan dibandingkan dengan data validasi, menunjukkan bahwa model terlalu mempelajari detail dan noise pada data pelatihan sehingga kurang mampu menggeneralisasi pola pada data baru. Oleh karena itu, diperlukan optimasi lebih lanjut seperti augmentasi data, regulasi model dan peningkatan jumlah data pelatihan untuk meningkatkan performa model dan mengurangi efek overfitting. Pengujian akurasi pengenalan gambar hewan pada aplikasi web ini dilakukan menggunakan dataset gambar hewan yang baru sebanyak 10 data gambar untuk masing-masing kelas, dengan nilai akurasi rata-rata untuk semua kelas hewan sebesar 54.67%. Dari 15 kelas hewan, nilai akurasi tertinggi diperoleh oleh kelas Zebra dengan nilai akurasi 90%, sedangkan kelas hewan Laba-Laba dan Kucing menjadi kelas hewan dengan nilai akurasi terendah sebesar 20%.
 
Kata kunci: Convolutional Neural Network (CNN), Aplikasi web interaktif, Pengenalan hewan, Klasifikasi gambar.

Indonesia memiliki potensi pariwisata sangat besar, salah satunya di provinsi Bali. Tetapi masih terdapat permasalahan sektor pariwisata seperti, informasi tempat wisata masih minim, sulit membandingkan jasa pramuwisata, dan testimoni pengguna yang kurang. Pernyataan ini disampaikan langsung oleh wisatawan dan pramuwisata, bilamana dibiarkan permasalahan ini dapat menimbulkan rasa skeptis. Maka dalam penelitian ini melakukan perancangan prototipe high fidelity aplikasi Go on Vacation yang mana bertujuan sebagai solusi permasalahan pramuwisata dan wisatawan. Rancangan aplikasi menggunakan metode User Centered Design (UCD), dimana terdapat empat tahapan yaitu, understand context of use, specify user requirements, design solutions, dan evaluation against requirements. Untuk menguji prototipe aplikasi menggunakan usability testing dengan tiga buah aspek, yaitu efektivitas, efisiensi dan kepuasan pengguna. Hasil pengujian pada rancang prototipe aplikasi Go on Vacation menghasilkan persentase completion rate efektivitas sebesar 100%. Efisiensi dengan overall relative efficiency menghasilkan persentase rata-rata sebesar 100% dan kepuasan pengguna pengguna dengan menggunakan USE Questionnaire, menghasilkan persentase 89,08% untuk antarmuka pramuwisata dan 94,52% dari sisi antarmuka wisatawan.
Kata Kunci: Prototipe, Pariwisata, UCD

Customer churn adalah kecenderungan pelanggan berhenti dan berpindah layanan dalam periode tertentu. Ini merupakan masalah utama dalam industri telekomunikasi karena mempengaruhi keuntungan perusahaan. Mempertahankan pelanggan lebih mudah dibandingkan mendapatkan pelanggan baru. Memprediksi churn membantu sektor CRM dalam merancang strategi retensi. Tingkat churn yang tinggi dapat menurunkan pendapatan dan mengganggu stabilitas bisnis. Berdasarkan studi, tingkat churn tahunan di industri telekomunikasi berkisar antara 15% hingga 30%. Data mining, yang memanfaatkan teknik pembelajaran mesin, digunakan untuk menganalisis dan mengekstraksi pengetahuan dari data. Penelitian ini bertujuan untuk membandingkan performa dua algoritma yaitu Random Forest dan Gradient Boosting. Hasil yang didapatkan menggunakan splitting data 80:20 menunjukkan bahwa klasifikasi lebih unggul menggunakan metode Gradient Boosting dibandingkan metode Random Forest dilihat dari tingkat akurasi dan nilai ROC AUC. Metode Gradient Boosting mendapatkan nilai akurasi dan ROC AUC sebesar 83% dan 0.89, Sedangkan metode Random Forest mampu menghasilkan nilai akurasi dan ROC AUC sebesar 81% dan 0.87.
 
Kata kunci: Churn, Gradient Boosting, Klasifikasi, Random Forest, Telco
 
 

Chicken and duck eggs are highly nutritious food products that are popular among the Indonesian community. However, their perishable nature leads to a decline in quality if not further processed. The salting process is a simple preservation method that can also enhance the flavor of salted egg products. To produce salted egg products with high organoleptic quality preference, a combination of Analytical Hierarchy Process (AHP) and Simple Additive Weighting (SAW) is implemented as a quality decision-making method based on: (1) the experts viewpoints on the importance level of organoleptic criteria, and (2) the scores of organoleptic tests for the criteria of texture, taste, and appearance. In this study, chicken and duck eggs were processed into salted eggs using a salting mixture made of a blend of scouring ash and table salt with a mass ratio of 5:4 and 5:6, resulting in product combinations coded as CE-5/4, CE-5/6, DE-5/4, and DE-5/6. Data processing results on the importance level from the experts viewpoints using the AHP method resulted that the criteria for texture, taste, and aroma had final priority weights of 0.244, 0.617, and 0.139, respectively. Final decision-making using the SAW method indicated that the highest to lowest final preference scores were obtained by products CE-5/4, DE-5/4, DE-5/6, and CE-5/6, with the final preference scores of 0.979, 0.963, 0.931, and 0.906, respectively. The results demonstrated that AHP and SAW were successfully implemented to assist in making decisions regarding the quality of salted egg products based on their organoleptic characteristics.
 
Keywords: salted egg, organoleptic, decision-making, AHP, SAW

This study aims to examine the evolution of Customer Relationship Management (CRM) implementation and its challenges in the digital economy over the past 15 years, focusing particularly on Small And Medium-Sized Enterprises (SMEs). A Systematic Literature Review (SLR) approach was employed, utilizing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, resulting in the analysis of 36 selected articles from an initial pool of 291. The results indicate a significant increase in CRM adoption, especially among SMEs during the COVID-19 pandemic, highlighting that CRM enhances customer loyalty, satisfaction, and operational efficiency while also fostering innovation. However, challenges such as high implementation costs, data security concerns, and a lack of technological knowledge persist. This research contributes to existing literature by providing insights into CRM adoption trends and challenges, emphasizing the need for integrated security measures and support for SMEs to maximize CRM benefits.

The financial sector has experienced significant transformation with the adoption of Artificial Intelligence (AI) technology, particularly in improving business decision-making. This study aims to analyze the impact of AI on decision-making quality, focusing on risk analysis and portfolio management in Indonesia's financial sector. A mixed-method approach was utilized, combining quantitative and qualitative data to provide a comprehensive view of AI’s role in financial decision-making processes. Quantitative data were gathered through surveys of 50 respondents from various financial institutions, while qualitative data were obtained from semi-structured interviews with industry executives. The findings indicate that AI significantly enhances risk analysis accuracy by 25%, optimizes portfolio management, accelerates decision-making processes, and improves operational efficiency by automating manual tasks and reducing human errors. Despite these benefits, the study also identifies challenges such as data quality issues and high implementation costs, which hinder the broader adoption of AI in the financial sector. The study concludes that AI offers substantial potential to improve decision-making in the financial industry, but addressing data infrastructure and training needs is critical for achieving optimal outcomes

Objective: We aimed to explore that the association of irisin with various anthropometric and metabolic parameters in obese diabetics and non-diabetics Iraqi women. Methods: Eighty obese Iraqi women participated in this cross-sectional study grouped into 40 obese and 40 obese diabetics. The correlation coefficient between circulating irisin levels and metabolic parameters were performed. Results: Serum irisin levels in obese group showed highly significant positive correlations with body weight, WC, BMI, FPG, fasting insulin (FI), HOMA-IR and glucagon (r=0.8684, P> 0.0001 ; r = 0.8104, P> 0.0001; r = 0.8285, P <0.0001; r = 0.5876, P> 0.0001?; r = 0.5283, P> 0.0005?; r = 0.0005, P <0.0001; r = 0.5244, P> 0.0005) respectively,  and significant negative correlation ?with FPG, FI and HOMA-IR (r=-0.3246, P<0.041; r=-0.7903, P<0.0001; r=-0.6105, P<0.0001) respectively. Stepwise regression results showed that body weight, FPG, HOMA-IR and glucagon had significant independently related with irisin (?=?2.3150, P<0.0001; ?=-?1.2200, P=?0.0002; ?=?21.8760, P=0.02?; ?=?-20.9800, P<?0.005; ?=?0.0468, P=0.037) respectively. Conclusions: Irisin had a strong positive correlation with anthropometric parameters. Irisin independently associated with body weight, glucagon, HOMA-IR and FPG

Digital innovation offers myriad advantages to companies but also entails risks necessitating mitigation. To safeguard against adverse impacts on both the company and its consumers, adherence to legal obligations is imperative. Privacy and security risks pose potential economic, ethical, or legal ramifications for consumers and companies alike. The duty to safeguard personal data is shared between governmental bodies and companies, with the latter assuming primary responsibility as service providers. Ethical business conduct entails the protection of user data and transparent disclosure of data usage to users. Companies also need to consider human, technological, and environmental aspects before developing new technologies. Therefore, awareness from companies is needed to fulfill their digital social responsibility. The latest regulation is Law Number 27 of 2022 concerning Personal Data Protection. Personal data protection is one of the main focuses of Corporate Digital Responsibility (CDR) or Corporate Digital Responsibility. The CDR concept is an evolution of Corporate Social Responsibility adapted to the digital era. In CDR, companies are expected to adopt practices that consider digital culture. It can be an effective strategy to integrate business and government interests in efforts to protect digital users.

The purpose of this study was to examine the effect of reward, punishment and psychology on academic cheating. This type of research is quantitative with a population of 39 students at Alhimni Education Center and a sample of 31 results from the purposive sampling method. The data used are primary data through questionnaires and measured by a Likert scale. The data analysis technique uses descriptive statistics through the SmartPLS testing tool with outer model and inner model measuring instruments. The results of the study showed that punishment had a negative and significant effect. While reward had a negative effect and psychology had a positive effect but both were not significant.

Sustainability report disclosure is becoming increasingly important for companies, and this can be seen from several perspectives, including corporate social responsibility (CSR), and investor confidence. This study aims to analyze the effect of disclosure of environmental, social, and economic performance on company mining sector on the IDX for the period 2019-2023. Using quantitative method with multiple linear regression through SPSS 25, the sample was taken with purposive sampling with a population of companies in the mining sector listed on the IDX. Sustainability report disclosure is measured using the GRI G4 index, while firm value is measured by Market to Book Value. The results show that environmental, social, and economic performance each has a positive and significant effect on firm value. Simultaneously, the three variables also have a significant influence on firm value.