cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Budi Hermawan
Contact Email
-
Phone
+62081703408296
Journal Mail Official
info@kdi.or.id
Editorial Address
Jl. Flamboyan 2 Blok B3 No. 26 Griya Sangiang Mas - Tangerang 15132
Location
Kab. tangerang,
Banten
INDONESIA
bit-Tech
Published by Komunitas Dosen Indonesia
ISSN : 2622271X     EISSN : 26222728     DOI : https://doi.org/10.32877/bt
Core Subject : Science,
Computer Science & IT
The bit-Tech journal was developed with the aim of accommodating the scientific work of Lecturers and Students, both the results of scientific papers and research in the form of literature study results. It is hoped that this journal will increase the knowledge and exchange of scientific information, especially scientific papers and research that will be useful as a reference for the progress of the State together.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 642 Documents
 58   59   60   61   62 
Bitcoin Price Prediction Using a Deep Learning Approach with an LSTM Algorithm Muhammad, Fathur Rahmansyah Maulana; Permatasari, Reisa; Najaf, Efrat Abdul Rezha
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3613

Abstract

The rapid advancement of digital financial technologies has accelerated the adoption of cryptocurrencies, with Bitcoin emerging as the dominant asset characterized by extreme price volatility and investment risk. Despite extensive studies on Bitcoin forecasting, existing predictive models remain limited in capturing long-term volatility dynamics and complex temporal dependencies, leading to unstable performance under fluctuating market conditions. This study addresses this gap by developing a deep learning-based forecasting framework using the Long Short-Term Memory (LSTM) algorithm integrated with a real-time web-based application. Historical Bitcoin price data were preprocessed through Min–Max normalization and transformed into time-series sequences using sliding window techniques. The proposed model consists of two stacked LSTM layers with 100 hidden units each, followed by a dense output layer, and was trained using the Adam optimizer with early stopping to prevent overfitting. Model performance was evaluated using Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Mean Absolute Error (MAE). The experimental results demonstrate that the proposed LSTM model achieved a Test MAE of 2.27%, indicating substantially higher accuracy compared to conventional statistical forecasting approaches reported in prior studies. The model effectively tracks long-term price trends, although extreme short-term spikes remain challenging due to inherent market volatility. Furthermore, the integration of the trained model into a Flask-based web application enables interactive real-time price prediction, representing a practical innovation beyond offline forecasting models. Overall, this research demonstrates the effectiveness of deep learning for supporting cryptocurrency investment decisions in real-world practice.
Text Pre-processing Techniques for the Fulfulde Language using NLTK Babgai Guidéké, Raphael; Vidémé Bossou, Olivier; Habiba, Missa
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3621

Abstract

The Fulfulde language, spoken by over 60 million people, presents significant challenges for Natural Language Processing (NLP) due to its complex morphology and dialectal diversity. Existing low-resource frameworks and standard rule-based approaches often fail to adequately address these morphosyntactic intricacies, creating a critical research gap. To bridge this gap, this study introduces the Text Pre-processing Technique for Fulfulde (TPTF). This pipeline engineer’s specific adaptations of conventional NLP techniques tokenisation, normalisation, lemmatisation, stop-word removal, and POS tagging tailored for Fulfulde's linguistic structure. The system was evaluated on a compiled corpus of 6,583 sentences from diverse media and literary sources, acknowledging the constraints inherent to such a low-resource dataset. Performance was assessed using ROUGE metrics to quantify the overlap and fidelity between automatic and reference pre-processing. The proposed technique achieved 99.22% precision, 61.73% recall, and an F-score of 76.11%. These results demonstrate TPTF's superior capacity to handle Fulfulde specificities compared to generic models. The TPTF pipeline provides a robust engineering foundation for downstream NLP tasks. Beyond technical performance, this contribution supports the future development of translation tools, aiding the preservation of Fulfulde's linguistic heritage and enhancing digital information access for its speakers.
Analysis of the LQ45 Stock Portfolio Using Mean–Variance Method and Cornish–Fisher Expansion Putri, Shafira Amanda; Trimono, Trimono; Muhaimin, Amri
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3640

Abstract

Public interest in stock market investment in Indonesia has increased alongside growing awareness of financial planning and portfolio management. The LQ45 Index, consisting of stocks with high liquidity, large market capitalization, and strong fundamentals, is widely used as a benchmark for portfolio analysis. However, many portfolio studies still rely on conventional Value at Risk (VaR), which assumes normally distributed returns and may underestimate extreme losses, making it less effective in capturing tail risk. This study addresses this research gap by integrating Mean–Variance Optimization (MVO) with the Cornish–Fisher VaR approach, which incorporates skewness and kurtosis to accommodate non-normal return distributions. Daily adjusted closing price data of LQ45 stocks from January to December 2025 were obtained from Yahoo Finance, and logarithmic returns were calculated. Based on the highest Sharpe Ratios, BRPT, EXCL, and ANTM were selected as portfolio constituents. Correlation analysis shows low dependency among the selected stocks, supporting diversification, while normality tests confirm deviations from normality, justifying the use of Cornish–Fisher VaR. The optimal portfolio allocates 10.6% to BRPT, 65.5% to EXCL, and 23.9% to ANTM, producing an expected return of 65.7%, portfolio risk of 26.2%, and a Sharpe Ratio of 2.5, indicating strong risk-adjusted performance. Cornish–Fisher VaR estimates potential losses of 2.23%, 3.09%, and 5.30% at the 90%, 95%, and 99% confidence levels. These results demonstrate that combining MVO and Cornish–Fisher VaR offers a more robust framework for portfolio optimization in the Indonesian stock market.
Hyperparameter Optimization of Hybrid LSTM-GRU using Genetic Algorithm for Stock Price Prediction Lumangkun, Mordekhai Gerin; Swari, Made Hanindia Prami; Sihananto, Andreas Nugroho
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3656

Abstract

Predicting stock prices in the banking sector, particularly for high-capitalisation stocks such as Bank Rakyat Indonesia (BBRI), remains challenging amid market volatility. While Hybrid LSTM-GRU models have demonstrated capability in capturing temporal dependencies in time-series data, prior studies have predominantly focused on manual tuning or optimization of single recurrent architectures, with limited application of Genetic Algorithms for optimizing hybrid recurrent networks in emerging stock markets (R1). This research aims to address this gap by implementing an evolutionary optimization framework using a Genetic Algorithm (GA) to automatically tune the hyperparameters of a Hybrid LSTM-GRU model for enhanced stock price forecasting accuracy. Historical BBRI data from November 2020 to June 2025 were preprocessed through normalization and transformed into supervised time-series sequences before being divided into training, validation, and testing sets. The GA was configured with a population size of 20, 80 generations, and a crossover rate of 0.8 to search for optimal learning rates, batch sizes, and hidden units. The optimized configuration identified 64 units for LSTM and GRU layers, a learning rate of 0.002, and a batch size of 16. The resulting model achieved an RMSE of 82.11 and an MAPE of 1.51%, representing a 20% error reduction compared to baseline hybrid models and outperforming benchmark approaches reported in prior studies (R1). Achieving a 1.51% MAPE indicates reliability for financial forecasting, supporting risk-sensitive investment decision-making (A). Overall, this study demonstrates that evolutionary hyperparameter optimization enhances hybrid deep learning architectures.
Optimization of a Web-Based Sweeping Order System Using Supply Chain Management Approach Aulia, Putri; Nugraha, Nugraha; Fergina, Anggun
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3657

Abstract

The order consolidation process, specifically "sweeping orders," is a critical yet often overlooked upstream activity in Supply Chain Management (SCM). At PT Flexo Solusi Indonesia, reliance on manual spreadsheet-based tools resulted in significant data fragmentation, entry errors, and processing delays, which severely hindered downstream logistics coordination and decision-making. This study aims to address this gap by designing and implementing a web-based sweeping order system integrated with SCM principles. Unlike typical inventory-focused systems, this research conceptually shifts the focus to "pre-processing" data synchronization to ensure early-stage supply chain integrity. The system development followed the Waterfall model, supported by a qualitative case study involving in-depth observation and interviews. To ensure research rigor, the system underwent comprehensive black-box testing and workflow validation, specifically evaluating indicators such as data accuracy, process traceability, and the elimination of redundant entry tasks. The results demonstrate that the centralized system successfully enforces sequential workflow validation, thereby mitigating data inconsistency risks and enhancing information flow between the warehouse, production, and shipping divisions. This study concludes that digitalizing upstream order consolidation is a prerequisite for achieving broader supply chain agility. It contributes to existing SCM literature by providing empirical evidence that operational efficiency is contingent upon the accuracy of initial data processing, serving as a scalable digital transformation blueprint for manufacturing SMEs.
Ethereum-Based Escrow System to Reduce the Risk of Peer-to-Peer Payment Abuse Kumala, Yudhistira Nanda; Parlika, Rizky; Maulana, Hendra
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3667

Abstract

Peer-to-peer (P2P) payments facilitate rapid direct transactions but are frequently compromised by trust asymmetry, leading to substantial risks of non-delivery or non-payment. This study addresses these vulnerabilities by introducing a lightweight, deterministic escrow mechanism based on Ethereum smart contracts, specifically designed to bridge the regulatory gap in consumer protection. Unlike conventional escrow systems that rely on costly human intermediaries or complex decentralized autonomous organization (DAO) structures, the proposed "FairPay" model advances the state-of-the-art by offering a streamlined five-state lifecycle architecture comprising Created, Funded, WorkSubmitted, Released, and Refunded stages. The research prioritizes an analytical problem-solution flow, focusing on a state-machine design that enforces automated role-based restrictions. Methodological evaluation conducted on the Ethereum Sepolia testnet demonstrates a 100% functional success rate across all unit test scenarios. Furthermore, gas cost analysis reveals that the system is economically viable for granular transactions, with core operational functions maintaining a low execution overhead. Beyond operational success, the primary scholarly contribution lies in the design insight of balancing high cryptographic security with granular transaction accessibility, providing a scalable framework for the modern digital economy. However, the system currently assumes binary participant decisions for work verification, representing a transparency-oriented limitation in handling highly subjective service deliverables. Ultimately, this study demonstrates that algorithmic trust, mediated through a simplified state-machine, offers a more efficient and transparent alternative to existing high-complexity blockchain models, effectively resolving the tension between decentralized security and practical usability in P2P digital interactions.
Evaluation of Information System Governance Using the COBIT 2019 Framework Novianti, Dian; Sunardi, Sunardi; Riadi, Imam
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3670

Abstract

Effective information system governance is a crucial factor in supporting the performance of higher education institutions, yet many universities still face challenges in implementing structured and standardized information technology governance. Evaluation of governance capability levels is necessary to identify weaknesses and determine appropriate improvement priorities. This study aims to evaluate the level of information system governance capability at the Faculty of Engineering using the COBIT 2019 framework and identify gaps between actual conditions and expected capability levels. This study uses a case study approach, adopting the APO, BAI, DSS, and MEA domains from COBIT 2019. Data collection was conducted through questionnaires, interviews, observations, and documentation, and the data were analyzed using the COBIT 2019 capability model and gap analysis. The results show that all information system governance domains are below the Level 3 (Established Process) target, with the DSS domain having the highest capability level and the MEA domain showing the lowest level, with the largest gap. Most processes are still at Level 2 (Managed Process), indicating they have been running but not formally documented or standardized. In conclusion, the identified capability gaps, particularly in the MEA and BAI domains, highlight the need for strengthening formal monitoring mechanisms, process standardization, and structured system development practices to enhance governance effectiveness, support strategic decision-making, and ensure sustainable information system management within the Faculty of Engineering.
Implementation of a Web-Based Customer Relationship Management System to Enhance Customer Loyalty Alfaraby, Feby; Alamsyah, Zaenal; Fergina, Anggun
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3676

Abstract

Customer Relationship Management (CRM) plays a critical role in sustaining customer relationships, particularly within SMEs in the retail sector that depend on repeat purchases. This study aims to examine how the IDIC (Identify, Differentiate, Interact, and Customize) framework can be operationalized under SME resource constraints through the design and evaluation of a web-based CRM system. Using empirical transaction records collected during an operational period, the study adopts a design-oriented empirical approach combining system development with IDIC-based analytical evaluation. The primary research contribution lies in the conceptual operationalization of the IDIC framework into implementable CRM modules rather than in proposing a novel technical architecture. Customer identification is achieved through centralized customer records, while differentiation relies on transaction frequency as a pragmatic behavioral indicator of repeat purchasing. Interaction is facilitated through automated reminder notifications, and customization is intentionally bounded to personalized reminders derived from transaction histories. System effectiveness is evaluated through a usability assessment involving 21 SME users, employing a five-point Likert-scale instrument that reports positive perceptions across usability dimensions, with mean scores exceeding 3.7. These findings indicate that limited CRM functionalities, when structured through a clear analytical model, can effectively enhance relationship-oriented practices. The abstract explicitly situates the study within a single-SME deployment context, clarifying its practical scope and limitations. Overall, the study demonstrates that an analytically grounded, resource-conscious CRM implementation can provide actionable insights for SMEs seeking to strengthen customer engagement and retention without adopting complex or costly CRM solutions.
Customer Segmentation-Based Promotion Recommendation Using RFM and K-Means Clustering on a Web Platform Handoko, Kemal Fiqri; Nugraha, Nugraha; Sujjada, Alun
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3677

Abstract

Traditional micro-scale retail businesses, such as neighborhood stores, frequently apply promotions uniformly due to limited analytical capacity, leading to inefficient resource use and weak customer retention. Existing promotion recommendation studies predominantly focus on large-scale or online retail settings, leaving a methodological and translational gap in data-driven promotional decision support for micro-scale traditional retail contexts. This study aims to address this gap by developing and evaluating a web-based promotion recommendation system tailored to operational constraints of small neighborhood stores. Customer purchasing behavior is modeled using the Recency, Frequency, and Monetary (RFM) framework, and customer segmentation is performed with the K-Means clustering algorithm. The study utilizes transaction records from 1,043 registered customers comprising 1,500 transactions collected between February and April 2025. Five customer segments are identified, namely VIP customers, frequent buyers, occasional shoppers, at-risk customers, and new customers. Clustering quality is assessed using the Silhouette Score, achieving a value of 0.4464, which indicates moderate cluster cohesion and separation. Promotional performance is evaluated through a pre–post implementation comparison, where the observed 157.09% sales increase reflects an associative improvement rather than a causal estimate of system impact. Analytically, the study contributes a validated customer segmentation pipeline suitable for sparse micro-retail data, while at the system level it delivers an operational web-based decision support tool that translates segmentation results into actionable promotional recommendations. Although practically useful, the evaluation covers one store and a short period, limiting generalizability and causal inference.
Multi-Criteria Teacher Performance Evaluation Using the SMART Decision Support Method Sehan, Achmad; Fadillah, Rezy Azril
bit-Tech Vol. 8 No. 3 (2026): bit-Tech
Publisher : Komunitas Dosen Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32877/bt.v8i3.3681

Abstract

Teacher performance evaluation plays a strategic role in sustaining instructional quality, yet existing appraisal systems in educational settings are often designed for conventional schools and lack structured computational frameworks capable of capturing the multidimensional demands of nature-based and spiritually integrated institutions. This study develops a web-based Decision Support System (DSS) integrating the Simple Multi-Attribute Rating Technique (SMART) to operationalize teacher performance assessment at Sekolah Alam Tahfidzpreneur, which combines academic instruction, Quran memorization, entrepreneurship, and outdoor learning. Unlike prior SMART-based implementations that primarily focus on score automation, this study formalizes weight rationalization, explicit benefit–cost criteria structuring, and utility normalization to enhance decision transparency and methodological replicability. Ten performance criteria were defined and weighted through institutional policy alignment, and teacher ratings were transformed into normalized utility scores to generate composite rankings. The system produced consistent performance stratification across eleven teacher alternatives, with top-ranked scores exceeding the institutional evaluation threshold. Efficiency gains and reduced subjectivity were inferred through comparative process mapping against the prior manual interview-based approach, demonstrating shorter evaluation cycles and explicit audit trails of weighting and scoring logic. By externalizing evaluation assumptions and computational procedures, the proposed DSS strengthens accountability and supports evidence-based professional development planning. The findings demonstrate that structured multi-criteria modeling can provide a transparent and replicable governance mechanism for complex hybrid educational environments.

Page 60 of 65 | Total Record : 642

 58   59   60   61   62 

Filter by Year

2018 2026


Reset
Filter By Issues
All Issue Vol. 8 No. 3 (2026): bit-Tech Vol. 8 No. 2 (2025): bit-Tech Vol. 8 No. 1 (2025): bit-Tech Vol. 7 No. 3 (2025): bit-Tech Vol. 7 No. 2 (2024): bit-Tech Vol. 7 No. 1 (2024): bit-Tech Vol. 6 No. 3 (2024): bit-Tech Vol. 6 No. 2 (2023): bit-Tech Vol. 6 No. 1 (2023): bit-Tech Vol. 5 No. 3 (2023): bit-Tech Vol. 5 No. 2 (2022): bit-Tech Vol. 5 No. 1 (2022): bit-Tech Vol. 4 No. 3 (2022): bit-Tech Vol. 4 No. 2 (2021): bit-Tech Vol. 4 No. 1 (2021): bit-Tech Vol. 3 No. 3 (2021): Remote Delivery Vol. 3 No. 2 (2020): Datamining Vol. 3 No. 1 (2020): Distance Learning Vol. 2 No. 3 (2020): Pandemik ICT Vol. 1 No. 3 (2019): Learning Synchronous and Asynchronous in the Industry 4.0 Vol. 2 No. 2 (2019): Support System Vol. 2 No. 1 (2019): Data Mining and Green Technology Vol. 1 No. 2 (2018): Data and Information Quality Vol. 1 No. 1 (2018): First Impression on Computing More Issue