Claim Missing Document
Check
Articles

Found 4 Documents
Search

IMPLEMENTATION OF DOUBLE EXPONENTIAL SMOOTHING METHOD IN WORLD GOLD PRICE PREDICTION APPLICATION Hizamrul Jaen; Cindy Rahayu
Bulletin of Engineering Science, Technology and Industry Vol. 1 No. 1 (2023): March
Publisher : PT. Radja Intercontinental Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59733/besti.v1i1.1

Abstract

The constantly changing price of gold in the world can worry gold investors, so accurate and fast data is needed to respond to these changes. The role of technology and appropriate procedures is crucial in addressing these challenges. This research will discuss the Prediction of World Gold Prices as a Support for Gold Stock Investment Decisions Utilizing Time-Varying Prediction Algorithms such as Double Exponential Smoothing, which utilizes historical data as a reference in the prediction calculation. The historical data sample used in this study ranges from the beginning of September 2019 to the end of October 2019. From this research, it is expected to test the Double Exponential Smoothing method in predicting future world gold prices.
IMPLEMENTATION OF LONG SHORT TERM MEMORY (LSTM) ALGORITHM FOR PREDICTING STOCK PRICE MOVEMENTS OF LQ45 INDEX (CASE STUDY: BBCA 2017 – 2023 STOCK PRICE) Cindy Rahayu; Dahlan Abdullah; Zara Yunizar
Bulletin of Engineering Science, Technology and Industry Vol. 1 No. 2 (2023): June
Publisher : PT. Radja Intercontinental Publishing

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59733/besti.v1i2.6

Abstract

This research aims to implement the Long Short Term Memory (LSTM) algorithm in predicting the movement of LQ45 stock prices. In this study, historical data of BBCA stock prices were used as an example of LSTM method implementation. The development process of the stock price prediction application begins with the collection of historical data, which then undergoes a preprocessing stage for normalization. The data is divided into training and testing sets, and transformed into suitable sequences for LSTM model input. The LSTM model is trained using the backpropagation through time algorithm and tested using the testing data. The predicted results from the LSTM model are compared with the actual labels using RMSE and MAPE metrics. Once satisfactory predictions are obtained, they are stored in a database and presented to users in the form of graphs and comparison tables. The implementation of LSTM in this research demonstrates prediction accuracy with an error percentage below 6%, with MAPE of 5.4772% and RMSE of 6.658%. Furthermore, the implementation of LSTM in the developed application using the latest historical data also yields low error percentages, with MAPE ranging from 3.7763% to 5.8048% for various stock price features. In conclusion, the LSTM method can be used for predicting stock price movements with satisfactory accuracy, providing valuable information for investment decision-making.
Access to Higher Education for Persons with Disabilities: A Document Study and Thematic Analysis of Structural Barriers and Reasonable Accommodations Neneng Tati Sumiati; Ajang Sopandi; Asep Taufik Muharram; Cindy Rahayu; Siti Ummi Masruroh; Gina Sagita
Mimbar Agama Budaya Vol. 42 No. 2 (2025)
Publisher : Center for Research and Publication (PUSLITPEN), UIN Syarif Hidayatullah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/mimbar.v42i2.50653

Abstract

Access to higher education for people with disabilities still faces structural and multidimensional barriers, as access does not stop at student admission but encompasses academic access, support services, information, and campus social participation. This study aims to map the main barriers and directions for improving higher education access policies for people with disabilities by referring to the non-discrimination and reasonable accommodation mandates in the CRPD. The method used is qualitative research based on document studies through thematic analysis of normative documents and authoritative reports (CRPD, OECD), as well as evidence of national and cross-country educational inequality (UNICEF Indonesia, World Bank). The results show that access to higher education is influenced by (1) uneven support and accommodation across institutions, which often makes meeting needs dependent on campus capacity; and (2) pipeline issues resulting from inequalities at previous levels, marked by low participation and graduation rates for groups with disabilities, thus narrowing opportunities to advance to higher education. These findings emphasize the need for an integrated access policy through minimum standardization of academic accommodations, strengthening disability service units, simplifying support procedures, and transition strategies from secondary education to higher education so that equal access can be achieved sustainably.
Segmentation of Adult Respondents’ Well-being Profiles Based on Daily Stress, Social Networks, Personal Resources, and Lifestyle Using Clustering Method Ajang Sopandi; Siti Ummi Masruroh; Neneng Tati Sumiati; Cindy Rahayu; Rona Nisa Sofia Amriza; Doni Febrian
The Journal of Indonesia Sustainable Development Planning Vol 7 No 1 (2026): April
Publisher : Pusbindiklatren Bappenas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46456/jisdep.v7i1.1071

Abstract

Existing literature on the topic of wellbeing mostly utilized scales and methods that are abstract and variable-centered yet assume homogeneity within the population being studied. This research utilizes a person-centered approach to classify the sample of 15,977 adults from a large-scale online survey about their wellbeing according to variables related to their stress, social networks, personal resources, and lifestyle. Factor analysis of mixed data (FAMD) is performed to reduce 22 variables of mixed types to 14 principal components that account for 77.51% of the variance in the data. Using these components, eight segments of well-being are classified by K-Means clustering and validated using Silhouette analysis. These segments range from those with low levels of stress, high levels of meditation, and clear goals for their lives to those with high levels of stress, no sense of accomplishment in their careers, and few social connections outside of work. Interestingly, another variable that was revealed as significantly different within each of the stress levels groups was the notion of whether or not the individual feels like they have enough money to cover their needs. Finally, the methods used in this research can be replicated to evaluate the wellbeing of the general population and to inform the creation of interventions to improve the lives of those with certain types of wellbeing profiles.