Selly Anastassia Amellia Kharis

Selly Anastassia Amellia Kharis

Auto-generated profile, based on publicly available information

Selly Anastassia Amellia Kharis

Universitas Terbuka

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 July 2024 in EDUKATIF : JURNAL ILMU PENDIDIKAN
Verified
Journal Article
Open access
PDF file
SKSelly Anastassia Amellia Kharis
Selly Anastassia Amellia Kharis
AIAnnisa Indriyani
Annisa Indriyani
The integration of artificial intelligence (AI), specifically ChatGPT, into education it may reduce social engagement among students and teachers also can diminish critical thinking skills, as students might prefer easy answers over deep, analytical thinking. This study investigates the social and psychological impacts of shifting student interactions from teachers to AI. The research method used is a literature study by reviewing seceral relevant and current literature. The result of this study is the reduction in face-to-face interaction can hinder the development of essential communication and collaborative skills between students and teachers as an impact of the intensity of AI use. Moreover, the dependency on AI could lead to a superficial understanding of subjects, with students accepting information at face value without thorough evaluation, thereby affecting their overall academic development and comprehension. Additionally, the study underscores the necessity of developing emotional intelligence, which AI cannot effectively nurture. The findings underscore the irreplaceable role of educators in nurturing cognitive and socio-emotional development, advocating for a balanced approach to integrating AI in education

1 April 2025 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
SKSelly Anastassia Amellia Kharis
Selly Anastassia Amellia Kharis
AZArman Haqqi Anna Zili
Arman Haqqi Anna Zili
Maulana MalikMaulana Malik
Maulana Malik
WNWahyu Nuryaningrum
Wahyu Nuryaningrum
APAgustiani Putri
Agustiani Putri
The financial market hold a significant role in the economy and the ability to accurately predict stock prices poses a major challenge, particularly in volatile markets like Indonesia. This study investigates the application of three supervised machine learning algorithms: random forest (RF), support vector regression (SVR), K-nearest neighbor (KNN) to predict the closing prices of stocks. The data used in this research consists of BBCA, PWON, and TOWR stocks. This study adopted daily historical stock prices from March 2017 to February 2020, which were normalized and segmented into training and testing datasets. The models were trained using machine learning techniques, and their predictive accuracy was evaluated using root mean square error (RMSE) and mean absolute error (MAE). The historical stock data includes Open, High, Low, and Close prices. The result indicated that SVR consistently outperforms RF and KNN in terms of RMSE and MAE across different stocks. The SVR method produced RMSE values of 4.79% for BBCA stock, 10.61% for PWON stock, and 15.14% for TOWR stock, and produces MAE values of 3.52% for BBCA stock, 8.49% for PWON stock, and 13.78% for TOWR stock.

24 November 2025 in BAREKENG: Jurnal Ilmu Matematika dan Terapan
Verified
Journal Article
Open access
PDF file
TSTri Wijayanti Septiarini
Tri Wijayanti Septiarini
SKSelly Anastassia Amellia Kharis
Selly Anastassia Amellia Kharis
Anuraga JayanegaraAnuraga Jayanegara
Anuraga Jayanegara
SASahidan Abdulmana
Sahidan Abdulmana
This study aims to (i) develop predictive models using statistical and fuzzy approaches, and (ii) evaluate their forecasting performance. The data were obtained from www.investing.com for the period 1961 to 2017 and focus on five ASEAN countries: Indonesia, Malaysia, the Philippines, Singapore, and Thailand. The statistical models used are Autoregressive Integrated Moving Average (ARIMA) and Exponential Smoothing, while the fuzzy approaches include Chen and Singh fuzzy time series models. The dataset was divided into training and test sets in a 75%-25% proportion. ARIMA models capture trends and autocorrelations in time series data, while Exponential Smoothing uses exponentially weighted averages. Fuzzy models are designed to handle uncertainty and linguistic patterns in data. The results show that Singh’s fuzzy model yields the lowest error for Indonesia, while exponential smoothing and Chen fuzzy time series model demonstrate the same lowest error for Malaysia. For the Philippines, exponential smoothing is most accurate, whereas ARIMA and Singh fuzzy time series achieve the smallest error for Singapore. For Thailand, exponential smoothing and ARIMA perform equally well. However, the robustness of the forecasting model cannot be determined from either statistical or fuzzy methods, highlighting the challenge in determining the most robust model for inflation in the ASEAN region. The 75%-25% data split may also limit the generalizability of the findings. This study contributes a rare cross-country comparison of statistical and fuzzy forecasting methods in the ASEAN context. It highlights the importance of model selection based on country-specific inflation behavior and provides insights for improving forecasting strategies in macroeconomic applications.

21 January 2021 in Jurnal Indonesia Sosial Sains
Verified
Journal Article
Open access
PDF file
AZArman Haqqi Anna Zili
Arman Haqqi Anna Zili
SKSelly Anastassia Amellia Kharis
Selly Anastassia Amellia Kharis
DLDian Lestari
Dian Lestari
Penelitian ini bertujuan untuk mendapatkan informasi penting dalam merencanakan penanggulangan pandemi, salah satunya adalah informasi terkait kematian akibat virus ini. Studi ini mencoba memprediksi angka kematian akibat virus corona di Indonesia. Studi ini menggunakan data kematian Indonesia akibat virus corona dari Maret 2020 hingga Desember 2020 untuk membentuk model ARIMA. Kemudian menggunakan model ARIMA untuk memprediksi angka kematian akibat virus corona hingga Januari 2021. Gunakan MAE untuk mengevaluasi keakuratan hasil prediksi, dan hasil prediksi MAE adalah 0,0007. Diharapkan hasil prediksi ini dapat digunakan pemerintah untuk merumuskan rencana pandemi virus corona.

31 July 2024 in BAREKENG: Jurnal Ilmu Matematika dan Terapan
Verified
Journal Article
Open access
FFFatia Fatimah
Fatia Fatimah
SKSelly Anastassia Amellia Kharis
Selly Anastassia Amellia Kharis
FFFauzan Ihza Fajar
Fauzan Ihza Fajar
In everyday life, we always encounter obstacles in seeing the interrelationships between several events to make the right decisions. Universitas Terbuka is a pioneer in distance education that implements digital transformation for new student registration, student services, and alums. The obstacle faced is determining a suitable promotion strategy for new students. As a result, a representative model is needed to handle such cases. As an extension of soft sets, N-soft sets can handle decision-making for binary and non-binary assessments. However, research has yet to be related to N-soft sets decision-making in data mining, especially association rule classification. This article proposes a new combination of N-soft sets with Association Rule (NSSAR). This article also introduces and applies the decision-making procedure using NSSAR to real. The population is new students of Universitas Terbuka Jakarta in the 2023/2024 odd semester. Samples were taken randomly using a questionnaire—primary data obtained by 201 new students. The following results are obtained based on the processed sample data using the NSSAR algorithm: 1) new students from Universitas Terbuka Jakarta are predominantly from Vocational High Schools domiciled in Bekasi, majoring in Bachelor of Management from the Faculty of Economics and Business; 2) The most favorite media information used by new UT Jakarta students is Instagram. Based on the results, the NSSAR algorithm gave relationship patterns between the number of new students based on region, study program, diploma of origin, and information media. Therefore, policymakers should consider the right promotional strategy to increase the number of students.

1 April 2024 in Paedagoria : Jurnal Kajian, Penelitian dan Pengembangan Kependidikan
Verified
Journal Article
Open access
PDF file
SKSelly Anastassia Amellia Kharis
Selly Anastassia Amellia Kharis
AZArman Haqqi Anna Zili
Arman Haqqi Anna Zili
Abstrak: Chat Generative Pre-trained Transformer (ChatGPT) adalah model bahasa generatif yang dikembangkan oleh perusahaan riset kecerdasan buatan OpenAI pada tahun 2015. Penggunaan ChatGPT dalam dunia pendidikan telah menimbulkan tantangan dan peluang khususnya pada pembelajaran abad 21 yang perlu dipertimbangkan secara seksama. Penggunaan ChatGPT seharusnya dipandang sebagai alat pendukung pembelajaran. ChatGPT tidak dapat menggantikan peran guru. Penelitian ini bertujuan untuk untuk mengidentifikasi tantangan dan peluang penggunaan ChatGPT sebagai alat pendukung pembelajaran. Penelitian ini menggunakan studi literatur dengan pendekatan kualitatif. Berdasarkan hasil penelitian, penggunaan ChatGPT dalam pendidikan dapat memberikan peluang untuk pengalaman pembelajaran yang interaktif, fleksibel, dan memperkenalkan siswa pada teknologi khususnya kecerdasan buatan. Hal ini sejalan dengan kompetensi pembelajaran abad 21. Namun penggunaan ChatGPT juga menimbulkan sejumlah tantangan seperti masalah integritas akademis, interaksi sosial, dan ketergantungan pada teknologi yang dapat mengurangi keterampilan berpikir kritis siswa. Untuk memanfaatkan ChatGPT secara efektif dalam pembelajaran diperlukan pendekatan holistik dan terpadu. Pengembangan kebijakan yang jelas mengenai batasan penggunaan ChatGPT dalam pembelajaran, penyesuaian model pembelajaran, dan peningkatan literasi digital siswa dapat diterapkan untuk menghadapi tantangan penggunaan ChatGPT. Dengan pemahaman yang mendalam tentang tantangan dan peluang penggunaan ChatGPT, pemangku kebijakan pendidikan, guru dan siswa dapat mempersiapkan diri dengan lebih baik untuk mengintegrasikan ChatGPT secara efektif dalam lingkungan pembelajaran.  The Chat Generative Pre-Trained Transformer (ChatGPT) is a generative language model developed by OpenAI in 2015. Its use in education presents challenges and opportunities, particularly in 21st-century learning, which require careful consideration. ChatGPT should be seen as a supportive learning tool and not a replacement for teachers. The research aims to identify the opportunities and challenges of ChatGPT as a learning aid, using a qualitative literature study approach. Based on research results, Its use in education offers opportunities for interactive, flexible learning experiences and introduces students to technology, especially artificial intelligence, aligning with 21st-century learning competencies. However, it also presents challenges such as academic integrity issues, social interaction concerns, and technology dependence potentially reducing students’ critical thinking skill. Effectively utilizing ChatGPT in 21st-century learning requires a holistic and integrated approach. Clear policy development regarding ChatGPT usage limits, adjustments to learning models, and enhancing students’ digital literacy can address these challenges. With a deep understanding of ChatGPT’s challenges and opportunities, education policymakers, teachers, and students can better prepare to integrate it effectively into the learning environment.