Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : Journal of Applied Data Sciences

A Comparative Study of Feature Selection Techniques in Machine Learning for Predicting Stock Market Trends Paramita, Adi Suryaputra; Winata, Shalomeira Valencia
Journal of Applied Data Sciences Vol 4, No 3: SEPTEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i3.99

Abstract

This study aims to compare the effectiveness of three feature selection techniques, namely Principal Component Analysis (PCA), Information Gain (IG), and Recursive Feature Elimination (RFE), in predicting stock market conditions. This research uses three distinct Kaggle datasets that contain data for predicting stock market values. The results show that RFE performs better than PCA and IG in predicting market value with fairly precise accuracy. By using the RFE technique, this study was able to identify the most influential features in prediction, reduce the dimensionality of the data, and improve the performance of the prediction model. These provide significant benefits in the world of stocks, including improved investment decisions, reduced investment risk, improved trading strategy performance, and identification of promising investment opportunities. For future research, further comparative studies between other feature selection techniques can be conducted. This research has novelty in several aspects. First, it applies different feature selection techniques, namely Principal Component Analysis (PCA), Information Gain (IG), and Recursive Feature Elimination (RFE), in the context of stock market prediction. Utilizing these techniques to select the most relevant features in predicting stock market conditions provides a deeper understanding of the influence of these features on stock price movements. Furthermore, this research utilizes different datasets from Kaggle, which represent various stock market value predictions. The utilization of diverse datasets provides variation in the data and allows this research to examine the performance of feature selection techniques in multiple stock market contexts. In conclusion, this research provides insight into the effectiveness of feature selection techniques in stock market value prediction. It also provides actionable guidance for market participants to improve investment decisions and trading performance in the stock market.
Modelling Data Warehousing and Business Intelligence Architecture for Non-profit Organization Based on Data Governances Framework Paramita, Adi Suryaputra; Prabowo, Harjanto; Ramadhan, Arief; Sensuse, Dana Indra
Journal of Applied Data Sciences Vol 4, No 3: SEPTEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i3.117

Abstract

Information systems research for non-profit organizations is an opportunity to make a contribution to the field of information systems, the adoption of information systems in this field is relatively tedious and there are few studies that examine this area; consequently, there are several research gaps in the domain of non-profit organizations that need to be solved. This research will focus on the development of data warehouse architecture and business intelligence for non-profit organizations. In this study, the Soft Systems Methodology (SSM) technique will be employed to develop a data warehouse architecture and business intelligence. This research will interview twenty individuals to collect primary data, review organizational policy documents, and conduct an open-ended survey. The obtained data will then be qualitatively analyzed, resulting in the formation of rich picture diagrams, CATWOE analysis, and conceptual models, which will ultimately form a data warehouse architecture and business intelligence. This research has produced a microservices-enhanced data warehouse architecture and business intelligence for non-profit organizations.
Implementation of the K-Nearest Neighbor Algorithm for the Classification of Student Thesis Subjects Paramita, Adi Suryaputra; Maryati, Indra; Tjahjono, Laura Mahendratta
Journal of Applied Data Sciences Vol 3, No 3: SEPTEMBER 2022
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v3i3.66

Abstract

Students who have studied for a considerable amount of time and will complete a lecture process must complete the necessary final steps. One of them is writing a thesis, a requirement for all students who wish to graduate from college. Each student's choice of topic or specialization will be enhanced if it not only corresponds to their interests but also to their skills. K-Nearest Neighbor is one of the classification techniques used. K-Nearest Neighbor (KNN) operates by determining the shortest distance between the data to be evaluated and the K-Nearest (neighbor) from the training data. K-Nearest Neighbor is utilized to classify new objects based on the learning data closest to the new object. Therefore, KNN is ideally suited for classifying data to predict student thesis topics. This research concludes that optimizing the k value using k-fold cross-validation yields an accuracy rate of 79.37% using k-fold cross-validation = 2 and the K-5 value. Based on the K-Nearest Neighbor Algorithm classification results, 45 students are interested in computational theory thesis (RPL) topics, 32 students are interested in artificial intelligence (AI) thesis topics, and 21 students are interested in software development topics.
An Unsupervised Learning and EDA Approach for Specialized High School Admissions Paramita, Adi Suryaputra; Ramadhan, Arief
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.178

Abstract

This research investigates disparities in access and representation within specialized high school admissions processes, focusing on public middle schools in New York City. Leveraging a dataset by a non-profit organization dedicated to increasing diversity in specialized high school admissions, the study employs exploratory data analysis and unsupervised learning techniques to identify schools with high levels of underrepresentation and academic potential. The analysis reveals significant disparities in access to specialized high schools, with certain demographic groups and schools facing barriers to entry. Through k-means clustering, schools are categorized based on their academic performance and demographic composition, enabling targeted intervention strategies to address disparities in access and representation. The research proposes general use towards education, including on-campus interventions, awareness campaigns, and regional information sessions, aimed at fostering equitable access to specialized high school programs. This study contributes to the broader discourse on educational equity and offers valuable insights for policymakers, educators, and researchers seeking to promote diversity and inclusion within educational systems.
Gold Prices Time-Series Forecasting: Comparison of Statistical Techniques Maryati, Indra; Christian, Christian; Paramita, Adi Suryaputra
Journal of Applied Data Sciences Vol 4, No 4: DECEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i4.135

Abstract

The fluctuation of gold prices throughout the year makes it difficult for both investors and regular individuals to predict the future value. The goal of this research is to utilize various statistical techniques, such as linear regression, naive bayes, and various types of smoothing algorithms, to predict the price of gold. The data used in this study was obtained from Kaggle and is from a 70-year time period. The results showed that using a single exponential smoothing method had the highest accuracy and precision, with a good MAPE score of 7.12%. This study is unique in that it compares multiple algorithms using data over a long time period, and it can be useful for investors and traders in making decisions related to gold prices. Additionally, it can also serve as a reference for future research studies.
Assessing Novice Voter Resilience on Disinformation During Indonesia Elections 2024 with Naïve Bayes Classifier Hari, Yulius; Yanggah, Minny Elisa; Paramita, Adi Suryaputra
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.489

Abstract

With the rise of social media platforms, the spread of fake news has become a significant concern. During the 2024 presidential election is dominated with novice voters, who are exposed to a lot of news from social media. As first-time voters, they get a lot of information and news exposure mainly from social media. This is also exacerbated by the fact that influencers are used to lead opinions. This research tries to measure the resilience of novice voters in dealing with hoax news compared with Naïve Bayes classifier to assessing the news. The purpose of this research is so that novice voters aware and are not easily polarized to prevent national disintegration due to disinformation and hoax news. Subsequently, this research also tries to develop a database of content and categories for hoax news from beginner voter data with a classification model. Data collection was carried out offline and online with interviews and questionnaires conducted with a total of 283 respondents from two private universities in East Java and came from various study programs. From the data, a classification approach using the naïve Bayes method was also built to help recommend a category whether this news is a hoax or news that can be verified. From the results of this study, it can also be concluded that the classification model with Naïve Bayes has a very good accuracy of up to 90.303% capable of categorizing a news story whether it is a hoax, dubious news, or valid news. In contrast, this study shows that the average accuracy of first-time voters is only 29.68%, which means that they are very vulnerable to hoax news, due to the many perceptions and assumptions in public comments that make views biased.
Fine-Grained Sentiment Analysis Approach on Customer Reviews Based on Aspect-Level Emotion Detection Paramita, Adi Suryaputra; Jusak, Jusak
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.964

Abstract

In the era of digital platforms, customer reviews constitute a vital resource for understanding user sentiment and perception toward products and services. Traditional sentiment analysis methods predominantly operate at the document or sentence level, often missing fine-grained emotional cues tied to specific product or service aspects. To address this limitation, this study proposes a novel Fine-Grained Sentiment Analysis (FGSA) framework that performs aspect-level sentiment classification using a joint learning approach. The proposed model employs a hybrid deep learning architecture that integrates transformer-based contextual encoders with Bidirectional Long Short-Term Memory (Bi-LSTM) layers. This design allows the model to capture both rich contextual semantics and sequential dependencies a combination that has not been widely adopted in existing FGSA research. Additionally, we introduce a new annotated dataset of 5,000 customer reviews spanning multiple domains (electronics, food and beverages, and general services), enabling robust training and evaluation. Experimental results show that the model outperforms standard baselines, achieving an F1-score of 82.0% for aspect extraction and an accuracy of 79.8% for sentiment classification. Further analysis reveals consistent patterns, such as positive sentiments linked to design and quality, and negative sentiments associated with customer service and delivery. These insights highlight the practical value of aspect-level sentiment modelling. The key contribution of this work is the integration of a transformer-Bi-LSTM joint architecture for aspect-based sentiment analysis, supported by a domain-diverse benchmark dataset. This framework enhances the interpretability and granularity of sentiment insights and sets a foundation for future research in multilingual and multimodal contexts.