Aung, Lynn Htet
Unknown Affiliation

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

Using Prophet for Accurate Time-Series Predictions of Doge Coin Aung, Lynn Htet
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 5 No 4 (2023): June
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.249

Abstract

Cryptocurrencies, including Dogecoin (DOGE), exhibit extreme price volatility and speculative behavior, making accurate price prediction a significant challenge for traders and analysts. This study applies Facebook Prophet, a robust time-series forecasting model, to predict Dogecoin's price movements using historical price and trading volume data. Prophet's ability to handle irregular datasets, missing values, and complex seasonality makes it well-suited for volatile financial markets. The methodology includes preprocessing the dataset, training Prophet on the “Close” price, and evaluating its predictive performance using metrics such as Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results reveal Prophet's capability to capture Dogecoin's underlying trends and seasonality, providing actionable insights into market behavior. By comparing Prophet's performance with traditional models like ARIMA and advanced deep learning techniques such as LSTM, the study underscores its strengths and limitations in cryptocurrency forecasting, contributing to the growing research on cryptocurrency analytics and offering a reliable framework for understanding and predicting price dynamics in highly volatile markets like Dogecoin.
Naive Bayes Classifier for Accurate Diabetes Diagnosis and Analysis Aung, Lynn Htet
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 5 No 3 (2023): March
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.254

Abstract

Diabetes mellitus is a chronic metabolic disorder with rising global prevalence, necessitating early and accurate diagnostic tools to mitigate complications. This study investigates the Naive Bayes classifier's efficacy for diabetes diagnosis, leveraging a dataset of 768 patient records encompassing clinical and demographic attributes, such as glucose levels, BMI, and insulin. Data preprocessing steps, including imputation, scaling, and normalization, ensure data quality, while feature selection identifies key predictors to enhance model performance. The classifier achieved an accuracy of 77%, with a weighted F1-score of 0.77, demonstrating robust performance for the "Not Worthy" class but moderate results for the "Worthy" class due to class imbalance and overlapping features. Ensemble methods, such as bagging and boosting, were explored to address these challenges, further improving robustness and recall. The study highlights the Naive Bayes classifier as a cost-effective, computationally efficient tool for real-time diabetes detection, with potential for deployment in resource-limited healthcare settings. Future research should focus on class balancing, advanced feature engineering, and validation on larger, diverse datasets to enhance diagnostic reliability and scalability.
Random Forest Analysis for Key Factors in Bitcoin Price Prediction Aung, Lynn Htet
Jurnal Sistem Informasi dan Komputer Terapan Indonesia (JSIKTI) Vol 6 No 2 (2023): December
Publisher : INFOTEKS (Information Technology, Computer and Sciences)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33173/jsikti.259

Abstract

This research explores the application of the Random Forest algorithm to predict Bitcoin price fluctuations. Given Bitcoin's high volatility and the influence of various factors such as market sentiment, macroeconomic variables, and blockchain-specific metrics, Random Forest was chosen for its capability to handle complex and non-linear relationships. The dataset includes trading volume, market capitalization, mining difficulty, and social media sentiment indicators. Data preprocessing techniques such as normalization, handling missing values, and adding temporal features were employed to enhance prediction quality. Model evaluation using Mean Absolute Error (MAE = 0.15), Mean Squared Error (MSE = 0.25), and R-squared (R² = 0.85) demonstrates the model's robust performance in capturing intricate market dynamics. The study highlights the importance of feature importance rankings in identifying key drivers of Bitcoin price movements, offering valuable insights for traders, regulators, and investors. Despite its success, areas for improvement include incorporating additional features, such as real-time sentiment analysis and advanced time-series predictors, to further enhance predictive accuracy and applicability across volatile market conditions.