Publication Search

Information technology is a technology used to manage data, including processing, acquiring, organizing, storing, and manipulating data in various ways to produce high-quality information—namely, information that is relevant, accurate, and timely. This information is used for personal, business, and governmental purposes, serving as strategic information in decision-making. To anticipate changes in weather conditions, particularly rainfall, a valid and accurate report is needed that can be useful for the public. So far, the correlation or relationship between the factors influencing weather conditions—especially rainfall—has not been precisely determined, making it mathematically difficult to create a model that can describe the correlation among all these factors. This is where Artificial Neural Networks (ANN) come into play: to create such models and map out the existing problems purely based on the input data provided. One of the capabilities of neural networks is to make predictions based on previously learned data using the backpropagation method.

This study explores employment development strategies aimed at bolstering economic growth in North Sumatra Province using the Vector Autoregression (VAR) model and an eighteen-year time series dataset. The variables analyzed include the Human Development Index (HDI), total population, Gross Regional Domestic Product (GRDP), Labor Force Participation Rate (LFPR), and Open Unemployment Rate (OUR). The estimation results reveal dynamic interrelationships among these variables over short, medium, and long-term periods. The VAR analysis with a lag of 2 illustrates how each variable contributes to both itself and the other variables. It also shows that past variables (t-1) significantly impact current variables. Furthermore, the response function analysis identifies how a change in one variable is responded to by others across different time horizons. Stability analysis confirms that all variables maintain medium-to-long-term stability over a five-year period. The Forecast Error Variance Decomposition (FEVD) highlights HDI, population, and GRDP as the most influential variables in shaping the employment system and economic development overall. The VAR model used meets the stability test criteria, making the findings a reliable basis for policy research.

The research entitled Production Planning of Tenun Ikat Petra Cilik in Kupang City aims to find out and explain the production planning of Tenun Ikat Petra Cilik in Kupang City. Data collection techniques in this study are observation, interviews, documentation and questionnaires. While data analysis techniques use forecasting and Break Event Point (BEP).The results showed that the amount of sales forecast for sarongs at Tenun Ikat Petra Cilik in 2024 was 174 sheets, in 2025 as many as 202 sheets and 2026 as many as 219 sheets. For blankets in 2024 as many as 107 pieces, in 2025 as many as 110 pieces and in 2026 as many as 113 pieces. For sashes on Tenun Ikat Petra Cilik shows that in 2024 there were 199 sheets, in 2025 there were 201 sheets and in 2026 there were 204 sheets. The results of the Break Event Point (BEP) analysis show that if Tenun Ikat Petra Cilik in Kupang City produces 101 pieces of sarong or Rp.152,000,000, for blankets producing 162 pieces or Rp. 162,857,142 and sling producing 1,380 pieces or Rp.411.940.298, then Tenun Ikat Petra Cilik will not make a profit or not suffer a loss because at that point Tenun Ikat Petra Cilik is in a state of basic return. And if the company produces below the BEP point, the company will experience a loss, and vice versa if the company produces above the BEP point, the company will experience a profit. Based on the results of the study, it is recommended that it be taken into consideration for the company in relation to making decisions on determining the number of orders and good planning for the supply of woven raw materials in order to smooth the production process in the company. And for the company, Tenun Ikat Petra Cilik needs to make a production plan or the amount of production to be produced appropriately in order to provide maximum profit. Produksi Keywords :Planning,Production    

This research is a case study with the object of research at UMKM Liwut Sari The purpose of this study is to determine and explain the production planning of herbal drinks at UMKM Liwut Sari. Data collection techniques in this research are observation, interviews, and documentation while data analysis techniques use forecasting and Break Even Point (BEP).  The results of the sales forecasting analysis of red ginger herbal drink and temulawak herbal drink at Liwut Sari UMKM in January are predicted to sell 263 packs of red ginger herbal drinks and 262 packs of temulawak herbal drinks, in February red ginger herbal drinks is 271 packs and temulawak herbal drinks is 270 packs, in March red ginger herbal drinks is 279 packs and temulawak herbal drinks is 278 packs. The results of the Break Even Point (BEP) analysis show that if UMKM Liwut Sari produces 86 packs of red ginger herbal drinks or Rp 4,289,855 and 81 packs of temulawak herbal drinks or Rp 4,054,794, then UMKM Liwut Sari does not make a profit or suffers a loss because at that point the company is in a state of principal return.

Bitcoin is one of the most prominent digital assets in the modern financial era due to its high volatility and huge profit potential. However, its extreme price volatility also makes it a high-risk asset, so a reliable forecasting approach is needed to help investors make more rational decisions. This study aims to forecast Bitcoin price using the Moving Average (MA) method, specifically MA3, by utilizing monthly historical data of Bitcoin price in USD currency obtained from investing.com website. The MA3 method was chosen for its ability to smooth out short-term fluctuations and identify the direction of price trends. The forecasting process is performed by calculating the average of the last three months' prices for each point in time and compared to the actual price to evaluate its accuracy. The evaluation is done using various prediction error metrics, namely Error, Absolute Error, Squared Error, and Percentage Error. The results of the analysis show that the MA method provides a fairly representative picture of price trends and can be used as an early indicator in short-term investment strategies. Thus, the Moving Average method proves to be a simple but effective prediction tool, especially for novice investors in the dynamic crypto asset market.

Poverty is one of the main problems that hinder regional development. Deli Serdang Regency shows a fluctuating trend in the number of poor people from year to year. To support government policies in overcoming poverty, an accurate forecasting method is needed to predict the number of poor people in the future. This study uses the Single Moving Average (SMA) method with two period variations, namely n = 2 and n = 3, based on data from the Central Statistics Agency (BPS) of Deli Serdang Regency for 2017–2023. The forecasting results show that the SMA method with n = 3 provides better accuracy than n = 2, as indicated by the Mean Squared Error (MSE) value of 21.38, Mean Absolute Deviation (MAD) of 4.44, and Mean Absolute Percentage Error (MAPE) of 3.52%. These findings indicate that the SMA method is capable of providing fairly accurate predictions and can be used as a basis for regional development policy planning to reduce poverty in Deli Serdang Regency in 2024.

The SMEs sector has an important role in supporting economic development in Indonesia. One of the sub-districts in Gresik, namely Sidayu, has many SMEs that are members of an association called ASUMSI. Almost all SMEs in these locations have not carried out a structured production planning. Production planning plays a vital role in a product-producing industry, including SMEs. Production planning can be started by forecasting demand. The results of this demand forecasting become the basis for production planning. This community service takes the theme of introducing the concept of demand forecasting which is expected to improve the production planning process for SMEs. This community service is carried out through counseling regarding the basic concept of demand forecasting for SMEs actors who are incorporated in ASUMSI. This community service is a form of academic participation in increasing the capacity of local resources, namely SMEs

Keputran Market is one of the main markets located in the middle of the city with a market area of ​​2550 m2, making Keputran Market have complex problems, especially parking areas. Keputran Market Surabaya is located in a densely trafficked location and Keputran Market Surabaya is located between 2 intersections, between Jalan Sulawesi, Jalan Dinoyo, and Jalan Pandegiling. The parking area available at Keputran Market Surabaya is 408 m2. This capacity is no longer adequate, so visitors cannot park in their proper places. Many motorbikes and cars choose to park on street. The large number of vehicles parked on street causes the available road capacity to narrow, often causing congestion. Based on the results of the analysis that has been carried out, the following results were obtained, Parking volume on peak days reached 343 vehicles with details of 281 for motorbikes and 62 for cars. While only 160 SRP are available, this means that the existing parking space is no longer able to be a parking lot to accommodate the number of vehicles. The average parking duration of motorcycles is 196 minutes per day, and the average parking duration of cars is 218 minutes per day. The turnover rate of motorcycles in one day reaches 2.10 times, then for cars in one day it reaches 2.38 times. Meanwhile, the forecast for vehicle parking growth that will occur in the next 5 years is increasing every year, where for motorcycles it is 10.64%, and cars are 7.13%. The 2021 SRP for motorcycles is 147 SRP and cars are 36 SRP. The 2022 SRP for motorcycles is 177 SRP and cars are 40 SRP. The 2023 SRP for motorcycles is 210 SRP and cars are 45 SRP. The 2024 SRP for motorcycles is 247 SRP and cars are 50 SRP. The 2025 SRP for motorcycles is 28 SRP and cars are 56 SRP. SRP in 2026 for motorcycles is 332 SRP and cars is 61 SRP.

The development of the digital ecosystem has disrupted the transportation sector. Traditional transportation businesses have shifted to online transportation. This study aims to analyze Blue Bird's strategy in facing the ride-hailing disruption in Indonesia. The research was conducted using a descriptive qualitative approach. The data was sourced from digital searches and observations. The results show that the digital transformation implemented by PT Blue Bird Tbk has improved operational efficiency and competitiveness in the highly competitive transportation market. The My Blue Bird application, with real-time tracking and cashless payment features, has streamlined the booking process and strengthened customer loyalty. The data indicates an increase in app usage and a reduction in operational costs, supporting the effectiveness of the company's digital strategy. Strategic collaboration with ride-hailing platforms has also significantly contributed to market expansion and increased fleet occupancy. The success of this strategy is reflected in the rise in booking volume and overall customer satisfaction. As a further step that has not been fully implemented, it is recommended that Blue Bird explore the application of AI-based predictive models to optimize fleet scheduling and route dynamics. The use of this technology can provide more accurate demand forecasts and support strategic decision-making in resource allocation. Additionally, the development of a customer feedback system integrated with digital analytics will allow the company to respond to consumer trends and preferences more effectively. These measures, supported by enhanced digital infrastructure and cross-sector collaboration, are expected to further boost Blue Bird's efficiency and growth in the digital disruption era.

The COVID-19 pandemic has exposed fundamental vulnerabilities in global supply chain systems, such as over-reliance on single suppliers and a lack of operational visibility. This has highlighted the urgent need for a new approach to risk management—one that leverages smart technologies. Artificial Intelligence (AI) has emerged as a promising solution, thanks to its capabilities in predictive analytics and adaptive, data-driven decision-making in real time. This study aims to develop an AI-based predictive system framework to enhance the resilience of global supply chains in the face of post-pandemic disruptions. Using the Design Science Research (DSR) methodology, the research designs and evaluates a system that integrates algorithms such as LSTM, Random Forest, Natural Language Processing (NLP), and Reinforcement Learning. It also applies a federated learning approach to ensure data privacy among supply chain partners. The study analyzes over 12,000 data entries from diverse sources, including IoT devices, weather data, demand trends, and social media. The system's effectiveness is evaluated through a combination of quantitative methods (PLS-SEM analysis on 103 respondents) and qualitative methods (interviews with 12 industry executives). The findings show that AI-driven predictive analytics significantly improve supply chain resilience (β = 0.67; p < 0.001), with demand forecasting accuracy increasing by up to 40% and delivery times reduced by 30%. Conceptually, the study contributes by designing a resilient model that integrates real-time visibility, adaptability, and cross-organizational collaborative learning. Unlike traditional approaches focused solely on automation, this framework offers a more holistic solution, addressing key gaps in the literature. The implication is clear: AI is becoming a strategic asset in building sustainable, resilient supply chains amid ongoing global uncertainty.

This study aims to evaluate production waste at PT XYZ, a food manufacturing company in Bandung, Indonesia, which experiences inefficiencies caused by overproduction and product defects. A descriptive qualitative method with a case study approach was used, employing data from production reports, field observations, and interviews. The analysis was conducted using the 7 Waste framework, the 5S workplace organization method, and the PDCA (Plan-Do-Check-Act) cycle. The findings show that the main types of waste at PT XYZ are overproduction and defects, which are caused by inaccurate demand forecasting, ineffective layout, and inconsistent quality control. By implementing 5S and PDCA, the company successfully reduced waste, improved workspace organization, and increased process efficiency. This study provides practical insights for manufacturing companies seeking to implement lean strategies for continuous improvement.

This study aims to analyze the influence of the Islamic financial sector on economic growth in Indonesia during the period 2014–2022. The Islamic financial components examined include Islamic stocks, sukuk (Islamic bonds), Islamic mutual funds, third-party funds from Islamic banking, and assets of Islamic non-bank financial institutions (IKNB). Economic growth is measured using Gross Domestic Product (GDP) as the dependent variable. The analysis employs a quantitative approach using the Vector Error Correction Model (VECM), complemented by Impulse Response Function (IRF) and Forecast Error Variance Decomposition (FEVD) to assess both short-term and long-term relationships. The results reveal that Islamic stocks and sukuk have a significant and positive effect on GDP in both the short and long term. Third-party funds from Islamic banks also contribute positively in the long run, although their short-run impact is insignificant. Conversely, Islamic mutual funds and IKNB assets show no statistically significant influence on economic growth. These findings highlight the strategic importance of strengthening Islamic capital market instruments and improving financial intermediation to foster sustainable economic development in Indonesia.

This study examines the application of big data analytics on Bhinneka.com, a leading e-commerce platform in Indonesia, to tackle the increasing in complexity of online user behavior in a swiftly changing digital environment. The primary issue is too challenges in evaluating extensive, unstructured, and heterogeneous user data, which obstructs personalization, marketing efficacy, and operational decision-making. The study seeks to assess the efficacy of big data instruments, specifically Artificial Intelligence Recommendation (AIRec) and Customer Data Platform (CDP), in improving user behavior forecasting. Service customization, and data-informed strategies. This study utilizes a qualitative case study methodology, including literature review and platform observation, to synthesis the many forms of big data analytics (descriptive, diagnostic, predictive, and prescriptive) and their implementation at Bhinneka.com. Significant findings indicate that the integration of AIRec and CDP has augmented the platform’s capacity to predict consumer preferences, improve marketing accuracy, and optimize logistics. However, obstacles stay the same, such as disjointed data systems, data quality concerns, and internal opposition to embracing a data-driven culture. The study suggests that although big data analytics substantially enhances Bhinneka.com’s digital competitiveness, ongoing investment in data infrastructure and organizational competence is crucial to fully harness its potential and preserve a competitive advantage in Indonesia’s e-commerce market.

This study aims to analyze the optimization of seaweed seedling inventory management using the Economic Order Quantity (EOQ) method to enhance cost efficiency for farmers in Tarakan City. The research employs a quantitative descriptive approach, integrating EOQ with forecasting techniques (Moving Average and Exponential Smoothing) to predict raw material needs accurately. Data were processed using Microsoft Excel and POM-QM for Windows to ensure precision. The results indicate that EOQ yields an optimal order quantity of 878 ropes per order, with a frequency of 6 orders per year, a reorder point of 16 ropes, and a total inventory cost (TIC) of IDR 842,681. Compared to traditional methods (TIC IDR 2,132,083), EOQ reduces costs by 60.5%. Forecasting analysis reveals that Exponential Smoothing (MAPE 19.67%) outperforms Moving Average (MAPE 22.5%) in accuracy. These findings highlight EOQ’s effectiveness in minimizing waste, preventing stockouts, and improving productivity. The study provides practical insights for coastal small-scale farmers and policymakers in the marine sector.

In geotechnical engineering, building robust structures is crucial to ensure the bearing capacity of structures against external forces, so making sure soil strength and unreliable build cost and duration prediction are also very important and preliminary aspects of any construction project. Therefore, in this first-of-its-kind modern examine, the capability of various artificially intelligent (AI)-based models toward reliable forecasting and estimation of preliminary construction expenses, duration, and strength at shear is explored. First, background information about the revolutionary artificial intelligence (AI) technique along with its many distinct models ideal for geotechnical and building engineering problems is presented, The use of AI-based models in the literature for the aforementioned construction and maintenance applications is discussed in a number of current works, together with their benefits, drawbacks, and future directions. Several important input elements that significantly affect the preliminary price of construction, construction time, and soil's shear strength estimation are listed and given through analysis. Finally, some obstacles to employing AI-based models for precise forecasts in these applications are discussed, along with elements influencing the problems with cost overruns. Thus, this work can help civil engineers make effective use of artificial intelligence (AI) to solve difficult and risky tasks. It can also be used to Internet of Things (IoT) environments for self-learning applications like smart architectural health-monitoring systems

BBPVP Semarang is a leading center for Fashion Technology and includes a subunit dedicated to Instructor Development for both government and private sectors, particularly in the field of Fashion Technology with a focus on Fashion Design Programs. It is the only work unit that offers an Upgrading Program in Fashion Design. The purpose of the upgrading program is to enhance knowledge in Fashion Design, which evolves annually based on trend forecasting and aligns with the needs of the business and industrial sectors. This study aims to describe and analyze the management of the upgrading program implemented by the Balai Besar Pengembangan Vokasi dan Produktivitas (BBPVP) Semarang, focusing on the planning, implementation, and evaluation phases. This research employs a qualitative approach using a case study method. Data collection techniques include interviews, observations, and documentation. The research uses source triangulation, involving 2 echelon 3 and 4 officials, 2 administrative staff members from Intala, 2 instructors, and 20 upgrading participants. Data were analyzed using an interactive analysis model, which includes data collection, data presentation, and drawing conclusions. The results show that the planning of the upgrading program at BBPVP Semarang involves identifying training needs, determining the training program, system, location, schedule, and methods, participant recruitment and selection, preparing human resources, training facilities, training schedule, and organization. The implementation of the upgrading program includes preparation, execution, assessment, responsibilities, and the issuance of training and competency certificates. The evaluation of the upgrading program includes aspects such as training materials, instructors, facilities and infrastructure, training materials, job readiness, meals, and boarding. In conclusion, the program management is running effectively and involves all elements, receiving positive appreciation from the participants.

Introduction: The integration of Digital Twin (DT) technology and the Internet of Things (IoT) into Building Energy Management Systems (BEMS) offers a transformative approach to optimizing energy consumption in buildings. This study explores the development of a Digital Twin based BEMS prototype, which leverages real time data collection, predictive analytics, and machine learning to enhance energy efficiency, reduce costs, and support sustainability goals in modern buildings. The research also addresses key gaps in current energy management systems, including real time adaptive control and integration with smart grid platforms. Literature Review: Previous research highlights the limitations of traditional BEMS, which often rely on static control strategies and lack real time adaptability. Recent advancements, including predictive maintenance and machine learning integration, have improved energy optimization. However, challenges such as data interoperability, scalability, and cybersecurity remain. This review consolidates current approaches and identifies opportunities for enhancing BEMS through the integration of DT technology, IoT, and machine learning. Materials and Method: The methodology employed involves the design of a Digital Twin based BEMS prototype, incorporating IoT sensors for real time data collection on variables such as HVAC load, occupancy, and environmental factors. The system uses time series forecasting and adaptive control strategies to optimize energy consumption. A case study building is used for validation, with performance metrics such as energy savings, CO₂ footprint reduction, and peak load reduction assessed to evaluate the system's effectiveness. Results and Discussion: The results demonstrate a significant reduction in energy consumption (up to 50%) compared to traditional BEMS, along with improved forecasting accuracy and sustainability performance. The prototype achieved a high R² score in predicting energy usage, validated through real world application in the case study building. The economic feasibility analysis showed substantial cost savings and a strong return on investment, making the system a financially viable solution for energy efficient building management.

In today’s global economy, accurately predicting foreign exchange rates or estimating their trends correctly is crucial for informed investment decisions. Despite the success of standalone models like ARIMA and deep learning models like LSTM, challenges persist in capturing both linear and nonlinear dynamics in highly volatile exchange rate environments. Motivated by the limitations of these individual models and the need for more robust forecasting tools, this study proposes a hybrid ARIMA-LSTM model that integrates ARIMA’s strength in modeling linear trends with LSTM’s capability to capture nonlinear dependencies, using historical USD/NGN exchange rate data from the Central Bank of Nigeria (CBN) spanning 2001 to 2024. The research hypothesis posits that the hybrid ARIMA-LSTM model will significantly outperform standalone models in forecasting accuracy. By comparing these models against state-of-the-art approaches, the study highlights the advantages of hybridizing statistical and deep learning methods. The findings demonstrate that the hybrid model achieved the lowest Root Mean Squared Error (RMSE) of 2.216 and the highest R² of 0.998, indicating superior forecasting performance. This study fills a critical research gap by demonstrating the effectiveness of hybrid deep learning in financial time series forecasting, providing valuable insights for investors, policymakers, and financial analysts. Future research will extend this work by incorporating the latest dataset and evaluating model robustness during the recent surge in the Naira/Dollar exchange rate from 2023 to 2024.

Rainfall potential analysis plays a critical role in the management of air resources, mitigation of hydrometeorological disasters, and agricultural activity planning. Accurate estimation of rainfall patterns is essential to ensure effective decision-making in irrigation systems, water resource management, and disaster risk reduction strategies. This study aims to model the probability of rainfall occurrence using a statistical approach based on historical data obtained from the Bureau of Meteorology. The data spans a multi-year period and captures seasonal and regional variability in rainfall events. To characterize rainfall patterns, various probability distributions are tested, including the exponential distribution and the Weibull distribution, which are commonly applied in hydrological studies. Furthermore, the Markov chain method is employed to assess the likelihood of rainfall occurrence on a given day based on the conditions of the preceding day, thereby capturing temporal dependencies. Parameter estimation is conducted using Maximum Likelihood Estimation (MLE), a robust statistical method that enhances the precision of the model. The suitability of each probability distribution in representing the observed rainfall data is evaluated through goodness-of-fit tests such as the Kolmogorov-Smirnov test. The findings reveal that certain distributions align more closely with the local rainfall characteristics, demonstrating the importance of regional analysis in climate modeling. The combination of probabilistic modeling, Markov analysis, and rigorous statistical testing provides a reliable framework for forecasting rainfall. These results are expected to serve as a scientific basis for stakeholders in agriculture, environmental planning, and disaster preparedness, offering insights that support sustainable water resource utilization and risk management.

Forecasting the number of electricity customers is a crucial aspect of resource planning and management at PT PLN Tasikmalaya. One method that can be used to improve forecasting accuracy is Lagrange Interpolation, which constructs an interpolation polynomial based on known data points. Although this method has been widely applied in various fields, its use in forecasting the number of electricity customers remains rare. Therefore, this study aims to explore the application of the Lagrange Interpolation method in forecasting the monthly number of electricity customers at PT PLN Tasikmalaya.In this study, historical electricity customer data was used as the basis for constructing an interpolation polynomial, which was then utilized to forecast the number of customers from January 2024 to May 2024. The forecasting results indicate an increase in the number of electricity customers each month. After rounding, the estimated number of customers is 274,952 in January 2024, 278,142 in February 2024, 284,402 in March 2024, 296,031 in April 2024, and 316,391 in May 2024.The findings of this study demonstrate that the Lagrange Interpolation method can be applied to forecast the monthly number of electricity customers at PT PLN Tasikmalaya. However, to improve forecasting accuracy, it is recommended to compare this method with other forecasting techniques and consider external factors that may influence the number of customers, such as government policies, economic growth, and changes in electricity consumption patterns.