Publication Search

This study examines the development of a Crude Palm Oil (CPO) price forecasting model using an artificial neural network algorithm, specifically the backpropagation algorithm. As one of Indonesia’s main export commodities, CPO has a significant economic impact and influences the income of oil palm farmers. The CPO price data used in this study were obtained from CIF Rotterdam, covering the period from January 2019 to December 2023. The research methodology consists of several stages, including data collection, preprocessing, model design, and model implementation using Python programming. The training results of the backpropagation algorithm show an error value of 0.537829578 after 1,000 epochs, while the evaluation using Mean Squared Error (MSE) indicates an MSE of 0.022709 during the training process and 0.017604 during the testing process. The model also produces CPO price predictions for the next three months, namely 932.578 for the first month, 949.568 for the second month, and 774.855 for the third month. These findings indicate that the developed model is capable of predicting future CPO prices with adequate accuracy, which can assist companies in making better financial decisions and managing risks associated with CPO price fluctuations.

The dynamic fluctuations in stock prices present a major challenge for investors in making informed decisions. To anticipate such uncertainties, forecasting methods that can provide accurate predictions are required. This study compares two time series forecasting methods Autoregressive Integrated Moving Average (ARIMA) and Double Exponential Smoothing (Holt) in predicting the stock prices of PT Telkom Indonesia (TLKM). The dataset consists of monthly closing prices from January 2018 to December 2023. The performance of each model is evaluated using three error metrics: Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The results show that the ARIMA(1,1,1) model yields higher predictive accuracy than the Holt method, with MAE of 787.71, MSE of 771,844.2, and RMSE of 878.55. In contrast, the Holt method records a MAE of 837.19, MSE of 878,393.4, and RMSE of 937.23. These findings confirm that ARIMA is superior in capturing the complex patterns of stock price movements and is more effective in volatile market conditions such as the stock exchange.

Perkembangan kecerdasan buatan (AI) mendorong inovasi dalam analisis keuangan, termasuk prediksi harga saham yang fluktuatif. Penelitian ini bertujuan memprediksi harga saham PT Garudafood Putra Putri Jaya Tbk menggunakan model ARIMA dengan penanganan Outlier sebagai pendekatan awal menuju sistem prediksi yang lebih adaptif. Data harga penutupan harian dari Yahoo Finance dianalisis melalui uji stasioneritas, identifikasi model ARIMA, deteksi Outlier berbasis log-return, serta evaluasi performa menggunakan RMSE, MAE, dan MAPE. Hasil penelitian menunjukkan bahwa ARIMA Outlier memberikan performa lebih baik dibandingkan ARIMA dasar. ARIMA standar menghasilkan MAPE 1.32% dan AIC –899.46, sedangkan ARIMA dengan tiga dummy Outlier mencapai MAPE 1.16% dan AIC –900.37. Peramalan 14 hari ke depan menunjukkan pola yang stabil pada kisaran Rp 370–371. Pada data uji, ARIMA dasar memberikan akurasi terbaik pada pertengahan Agustus, sedangkan ARIMA Outlier mencapai akurasi tertinggi pada akhir Agustus dengan prediksi Rp 370.2 yang sangat dekat dengan harga aktual Rp 370.4. Hasil ini menunjukkan bahwa penanganan Outlier meningkatkan ketepatan model, sehingga ARIMA Outlier dapat digunakan sebagai fondasi awal menuju pengembangan sistem prediksi keuangan berbasis AI.

Polusi udara partikulat halus (PM2,5) merupakan ancaman serius bagi kesehatan masyarakat di Kabupaten Brebes, Jawa Tengah. Faktor penyumbang utamanya adalah emisi kendaraan di jalur Pantura, aktivitas industri perikanan, serta konsentrasi tinggi selama musim kemarau (Juni–November). Tidak adanya model peramalan sub-jam yang akurat menghambat pengembangan sistem peringatan dini yang efektif. Penelitian ini mengembangkan dan mengevaluasi model deep learning berbasis Transformer untuk memprediksi konsentrasi PM2,5 dengan resolusi waktu 15 menit. Data yang digunakan berasal dari NASA GEOS-CF (band PM25_RH35_GCC) yang diakses melalui Google Earth Engine menggunakan API Python. Dataset mencakup periode 1 Januari hingga 22 November 2025, menghasilkan 7.813 observasi per jam, yang kemudian diinterpolasi linear menjadi 31.249 titik data dengan resolusi 15 menit. Arsitektur Transformer terdiri dari 3 lapis enkoder, 4 kepala perhatian multi-head, dimensi embedding 128, dimensi feed-forward 256, panjang sekuen 60 timestep, dan augmentasi fitur menggunakan rerata bergulir (*rolling mean*, jendela = 3) dan beda pertama (*first difference*). Pelatihan dilakukan dengan TensorFlow-Keras, pengoptimal Adam, penjadwal peluruhan kosinus (*cosine decay scheduler*), dan fungsi kerugian Huber. Pembagian data dilakukan secara kronologis: 70% pelatihan, 30% validasi. Evaluasi pada set uji independen (16 Agustus–21 November 2025, 9.357 observasi atau 97 hari 11 jam 15 menit) menghasilkan MAE 0,7691 µg/m³, RMSE 1,2052 µg/m³, R² 0,9945, dan *Explained Variance Score* 0,9948. Model ini mampu menggambarkan variasi diurnal dan anomali musiman secara akurat, jauh melampaui model LSTM dan GTWR konvensional. Penelitian ini memberikan kontribusi signifikan di bidang Teknologi Informasi melalui kerangka kerja pengolahan *big data* satelit untuk aplikasi lingkungan.

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.

Accurate sales forecasting is essential for stakeholders to make strategic decisions. This study aims to compare the performance of two deep learning models, namely Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN), in forecasting domestic motorcycle sales produced by AISI member manufacturers. The forecast is based on historical data from January 2021 to December 2024. The model was trained using time series data and the forecasting results for the period January to March 2025 were evaluated using the metrics Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The results show that the LSTM model produces lower MAE and MAPE values than CNN, which shows its superiority in providing more accurate and consistent predictions. On the other hand, the CNN model has lower RMSE and MSE values, thus being able to reduce large prediction errors. By comparing the results of LSTM, CNN, and actual data forecasting, the LSTM model is more suitable for forecasting motorcycle sales in Indonesia

XYZ is a manufacturing company that produces Yamaha brand motorbike parts such as electrical switches, electrical sockets, lever assembly and horns. Many of the products sent were returned by customers because they did not meet quality standards, for example in March 2024 there were 1,420 pcs out of a total of 19,900 pcs that were returned. This means that companies have to increase production time and costs to replace defective products that are returned because they do not have safety stock. Forecasting is needed to control the production system so that it does not experience over stock and safety stock shortages. This research aims to provide recommendations for forecasting methods that companies can use to minimize the occurrence of production excesses and shortages in the company. Forecasting is done based on historical company sales data for 12 months. The method used is the exponential smoothing method which is then tested whether this method can be used in the future. This calculation uses the help of POM-QM (Production Operation Management – Quantitative Method) software. Calculations are carried out by testing the MAD, MSE, and MAPE values to obtain calculation error values. The results obtained by forecasting the main sw srtg lock assembly product using the exponential smoothing method were 15,708 for demand for the next period, MAD 3.38, MSE 22.84 and MAPE value 26%. Based on these results, the exponential smoothing method can be a recommendation for companies to forecast future demand. This is because the value of forecasting accuracy or MAPE is reasonable. The smallest percentage of MAPE values has a fairly minimal possibility of error in forecasting results.

MSMEs are productive economic businesses run by individuals or small business entities to grow and develop their businesses in order to build the economy, so that MSMEs become the most important pillars in the Indonesian economy. The large number of competitors in the business world requires entrepreneurs to find strategies that can increase the sales cycle and fulfill the number of requests. Solusi Cash & Kredit is a company engaged in cash and credit sales of smartphones, furniture, and electronics. According to the owner of Solusi Cash & Kredit, Vivo smartphones are one of the best-selling brands on the market. The phenomenon that occurred in the company during August 2023 to June 2024 was the occurrence of fluctuations or instability in product sales levels. The purpose of this study was to determine the results of the comparison of sales forecasting with the Exponential Smoothingi and Least Square methods. The results obtained were that the exponential smoothing alpha 0.3 method had a MAPE value of 18.27% with a forecast value for the next period of 34 units per month. Alpha 0.5 had a MAPE value of 14.74% with a forecast value for the next period of 36 units per month. Alpha 0.7 had a MAPE value of 12.64% with a forecast value for the next period of 36 units per month. Alpha 0.9 had a MAPE value of 11.7% with a forecast value for the next period of 37 units per month. The least square method had a MAPE value of 7.2% with a forecast value for the next period of 41 units per month.

Forecasting demand for screen-printed clothing products at the UMKM "D'mitz Screen Printing" in Sobrah Village, Wungu District, Madiun Regency helps with production control planning to maximize supply chain management for screen-printed clothing products. To predict future product demand, it is very important for UMKM to forecast market demand. Forecasting future demand is very important to avoid sales prediction errors that can cause waste, such as increased production costs due to sales predictions being too large, or stock outs due to sales predictions being too small, which results in customers having to wait longer to get the goods they want. Based on this problem, the UMKM "D'mitz Screen Printing" carried out a demand forecasting analysis for screen printed clothing with the aim of reducing waste and maximizing value. Forecasting demand for screen printed clothing for the next five months using time series analysis and moving average methods. Forecasting results for the period March 2022 to February 2023 show sequential forecasting values of 3266.67; 3300; 3250; 3283.33; 3233.33; 3316.67; 3333.33; 3372.22; 3305.56; and 3272.22. From the Mean Absolute Error (MAE) and Mean Square Error (MSE) calculations that have been carried out, the MAE value is 94.44 and the MSE value is 16018.593.

Furniture raw materials are still a major challenge in the industry, in line with the wishes of consumers to get good quality raw materials and soaring export demand, so there is a need for a control process to monitor the value of products using forecasting. The purpose of this study was to predict gross domestic product in the furniture industry in Indonesia in 2022. This study used secondary data on the quarterly trend of gross domestic product in the furniture industry in Indonesia 2010-2021 taken from the research industry data processed by BPS and Bank Indonesia, The method used is Double Exponential Smoothing-Holt. The results of the calculation using the double exponential smoothing-holt method obtained a value of α of 0.658 and β of 0.008 where the forecasting results for the 2022 period, namely the 1 quarter of 7.602 billion rupiah, quarter 2 of 7.676 billion rupiah, quarter 3 of 7.749 billion rupiah, and quarter 4 of 7.822 billion rupiah. Where the MAPE value is 0.737% which means forecasting has very good results.

Sprite drink is a soda drink that is very popular among all groups. Demand is uncertain and always changes from time to time, making product availability difficult to control and often causes overstock or stockout problems. Therefore, inventory control is needed, which can be done by forecasting, determining safety stock and good re-order points. To obtain effective and efficient planning, the number of orders must be based on the number of past mass requests so as to reduce the occurrence of overstock or stockouts. With the problems experienced by PT. XYZ, the forecasting method used is the time series forecasting method. In this case, the time series methods used are Simple Average, Single Moving Average and also Single Exponential Smoothing. After carrying out several calculations, we obtained a Mean Absolute Centage Error (MAPE) value of 49.379%, a Mean Absolute Deviation (MAD) of 2297.145, a Root Mean Squared Error (RMSE) of 2912.495 and also a Mean Squared Error (MSE) of 8,482 .628 and forecasting results of 4504 pcs every month. Based on the calculation results, the proposal given is to reorder Sprite 250ML when the inventory in the warehouse reaches 1548 pcs with a safety stock of 540 pcs.

Peramalan merupakan proses untuk memperkirakan beberapa kebutuhan di masa yang akan datang, yang meliputi kebutuhan dalam ukuran kuantitas, kualitas, waktu dan lokasi yang dibutuhkan dalam rangka memenuhi permintaan barang atau pun jasa. Penelitian ini bertujuan untuk meramalkan jumlah angkatan kerja di Kota Medan menggunakan metode Trend Non Linear Kubik. Data yang diperlukan untuk penelitian ini adalah data jumlah angkatan kerja di Kota Medan dari tahun 2011-2020 dan Sumber data penelitian ini diperoleh dari Badan Pusat Statistik (BPS) Kota Medan. Data tersebut dianalisis dengan metode Trend Non Linear Kubik  untuk meramalkan jumlah angkatan kerja pada tahun 2021 dan pengolahan datanya menggunakan software SPSS. Hasil analisis Model peramalan jumlah angkatan kerja di Kota Medan menggunakan metode Trend Non Linear Kubik diperoleh persamaan modelnya adalah y=512819+155612x-28928x^2+1754x^3 dan hasil keakurasian model sebesar 3,94%, peramalan yang dilakukan menghasilkan jumlah angkatan kerja di Kota Medan untuk tahun 2021 adalah 1.058.837.

Perum Bulog as a State-Owned Enterprise has the main task, which is to conduct a quality and adequate basic food logistics business for the survival of the people. The problem that occurred in Perum Bulog Sub Divre Medan is that the rice supply in Bulog does not consider the demand in the market. Forecasting is an important tool in effective and efficient planning. Therefore, prediction is indispensable for predicting future events. This method essentially uses past data initiated by performing an exponentially decreasing weighting of older observational values or newer values. Brown's double exponential smoothing is a linear model proposed by Brown. This double exponential smoothing method is used when the data indicate a trend. In this study, the terbaik best parameter for forecasting the Number of Rice Sales in Perum Bulog Sub Divre Medan was α = 0.2 with MAPE of 0.27%. And the results of the forecast for Rice Sales at Perum Bulog Sub Divre Medan in 2022 are decreasing every month.

Abstrak – Wabah Covid 2019 adalah penyakit menular serta dapat menyerang organ pernapasan yang sangat mematikan di Negara Tiongkok. Masyarakat Indonesia yang terjangkit virus Covid 2019 ini perlu dilakukan peramalan untuk mengetahui jumlah kasus masyarakat yang terjangkit wabah Covid 2019 pada bulan berikutnya. Dengan menggunakan Metode Single Exponential Smoothing, Double Exponential Smoothing, dan Triple Exponential Smoothing ini kita gunakan pada aplikasi RStudio untuk mengetahui nilai parameter α, β, dan γ kita dapat mengetahui perbandingan dari ketiga metode tersebut. Dari ketiga metode tersebut akan menggunakan parameter nilai α, β, dan γ. Dari ketiga metode tersebut dicari nilai SSE yang terkecil. Dengan mengetahui nilai SSE yang terkecil maka akan di dapatkan hasil peramalan yang lebih akurat. Data yang saya gunakan berjumlah 30 periode. Dengan menggunakan 30 periode kita mendapatkan nilai SSE terkecil 33042318. Dengan nilai tersebut kita mendapatkan nilai coefficient 1179.6161 atau masyarakat yang terjangkit wabah covid 2019 pada hari berikutnya berjumlah 1741 orang. Dengan dilakukannya penelitian ini diharapkan untuk setiap masyarakat dapat menjaga kesehatannya dengan cara menjaga kesehatan, kebersihan, serta mengkonsumsi makanan yang sehat dan bergizi sehingga dapat terhindar dari virus covid-19. Dengan menggunakan Metode Single, Double, Triple Exponential Smoothing kita dapat meramalkan kasus covid-19 di Indonesia selama beberapa bulan kedepan.   Abstract – The 2019 Covid outbreak is an infectious disease and can attack the respiratory organs which is very deadly in China. For the Indonesian people who have been infected with the 2019 Covid virus, forecasting needs to be done to find out the number of community cases infected with the 2019 Covid outbreak in the following month. By using the Single Exponential Smoothing, Double Exponential Smoothing, and Triple Exponential Smoothing methods, we use the RStudio application to determine the value of the parameters α, β, and γ we can find out the comparison of the three methods. Of the three methods will use the parameter values ​​ α, β, and γ. From the three methods, the smallest SSE value is sought. By knowing the smallest SSE value, more accurate forecasting results will be obtained. The data that I use is 30 periods. By using 30 periods, we get the smallest SSE value of 33042318. With this value we get a coefficient value of 1179.6161 or the people who were infected with the 2019 covid outbreak on the next day amounted to 1741 people. With this research, it is hoped that every community can maintain their health by maintaining health, hygiene, and consuming healthy and nutritious food so that they can avoid the Covid-19 virus. By using the Single, Double, Triple Exponential Smoothing method, we can predict COVID-19 cases in Indonesia over the next few months.

Pembangkitan energi harus dapat direncanakan dan disesuaikan. Rencana produksi ditentukan berdasarkan prediksi kebutuhan energi masa depan dan ketersediaan energi baru dan terbarukan. Sistem Pembangkit Listrik Tenaga Surya dan Pembangkit Listrik Tenaga Angin adalah Pembangkit Energi Baru Terbarukan dengan sistem tenaga mandiri, yang memiliki kondisi sumber daya terbaik, dan memiliki prospek aplikasi yang baik. Sehingga perlu adanya penelitian yang mendalam tentang peramalan potensi energi tersebut. Pendekatan penelitian adalah melakukan peramalan potensi energi pembangkit listrik tenaga surya (PLTS) dan pembangkit listrik tenaga angin (PLTB) dengan menggunakan model Jaringan Syaraf Tiruan (JST) Multi Layer Perceptrons (MLP). Hasil penelitian menunjukkan bahwa peramalan potensi energi PLTS dan PLTB Jawa Tengah tahun 2025, PLTS 0,0093% konsumsi energi di Jawa Tengah dan PLTB 0,407% konsumsi energi di Jawa Tengah.

Peningkatan pertumbuhan penduduk di Semarang berbanding lurus dengan peningkatan kebutuhan sampah dan listrik. Persoalannya, sampah hanya berpindah dari tempat pembuangan sampah ke tempat pembuangan akhir. Hal ini menyebabkan munculnya dampak buruk terhadap lingkungan kota yang kotor. Di sisi lain, permintaan kebutuhan listrik yang tinggi setiap tahunnya meningkat. Untuk mengatasi masalah ini adalah pemborosan telah dimanfaatkan bahan pembangkit listrik. Dua parameter telah diusulkan untuk memprediksi potensi pembangkit listrik tenaga sampah di kota Semarang seperti populasi dan sampah. Algoritma backpropagation dari JST telah digunakan untuk memprediksi pembangkit listrik tenaga sampah untuk tahun 2020 hingga 2022. Variabel yang digunakan dalam peramalan meliputi ukuran populasi dan volume sampah. Hasil penelitian menunjukkan bahwa produksi listrik WPP adalah 8,8 MWH untuk peramalan 3 tahun. sedangkan pertumbuhan orang ditunjukkan sebagai 1,7 juta selama 3 tahun. Potensi pembangkit listrik sampah PLN telah diberikan 0,29% dari total kebutuhan listrik di Jawa Tengah.

Abstrak – Obat merupakan bahan biologis yang sangat penting digunakan untuk penyembuhan dan peningkatan kesehatan untuk manusia. Kebutuhan obat akan semakin terus meningkat seiring dengan menuanya penuduk, sehingga diperlukan peramalan penjualan ketersediaan obat. Peramalan merupakan proses menyusun informasi untuk mendapatkan informasi yang baru. Peramalan memiliki banyak metode, pada penelitian ini menggunakan Metode Single, Double, dan Triple Exponential Smoothing dengan menggunakan studi kasus obat. Ketiga algoritma ini akan dilakukan perbandingan untuk mengetahui metode mana yang terbaik dalam peramalan. Hasil penelitian ini menunjukan metode Triple Exponential Smoothing merupakan metode yang terbaik degan nilai SSE 3306.302, jika dibandingan dengan Singel Exponential Smoothing sebesar 3945.069 dan Double Exponential Smoothing sebesar 4673.829.   Abstract – Medicine is a very important biological material used for healing and improving health for humans. The need for drugs will continue to increase along with the aging of the population, so it is necessary to forecast sales of drug availability. Forecasting is the process of compiling information to obtain new information. Forecasting has many methods, in this study using the Single, Double, and Triple Exponential Smoothing method using drug case studies. These three algorithms will be compared to find out which method is the best in forecasting. The results of this study indicate that the Triple Exponential Smoothing method is the best method with an SSE value of 3306,302, when compared with Single Exponential Smoothing of 3945,069 and Double Exponential Smoothing of 4673,829.

CV. Ida Ayu adalah sebuah perusahaan yang bergerak di bidang perdagangan umum seperti tas rapat dan blocknote. Tujuan dilakukannya penelitian ini adalah untuk merancang sistem informasi pendukung keputusan pembelian barang yang dapat menghasilkan informasi yang valid, cepat dan akurat dan untuk mengetahui bagaimana membangun sistem informasi pendukung keputusan pembelian barang yang efektif dalam peramalan penjualan. Sulitnya administrasi untuk merancang suatu sistem informasi pendukung keputusan pembelian barang yang valid berdasarkan peramalan penjualan dan membuat sistem informasi pendukung keputusan pembelian barang yang efektif dalam meramalkan penjualan pada CV. Ida Ayu Semarang. Pada aplikasi peramalan ini metode yang digunakan adalah metode moving average. Metode ini diperoleh melalui penjumlahan dan pencarian nilai rata-rata dari sejumlah periode tertentu, setiap kali menghilangkan nilai terlama dan menambah nilai baru. Hasil penelitian diharapkan dapat menunjukan bahwa perancangan sistem informasi pendukung keputusan pembelian barang berdasarkan peramalan penjualan berbasis web dapat membantu karyawan (administrasi) untuk meminimalkan terjadinya kesalahan pembelian barang dengan mempertimbangkan penjualan yang terjadi dalam periode tertentu. Jadi semua kegiatan penjualan serta pembelian barang di CV. Ida Ayu dapat berjalan secara efektif dan efisien.

Forecasting is an estimate of future demand based on several forecasting variables based on historical time series or a process of using historical data (past data) that has been owned to use this model and use this model to estimate future conditions.The Ivori mini market SME group is known to be a mini market that sells daily necessities. The goods provided by the ivori mini market are not focused on only one type of goods, but include all types of goods. Ivori mini market often runs out of stock because there is no inventory planning. The main purpose of making this application is to assist employees in determining inventory planning that must be provided next month. While the method used to make this forecast is a single moving average, one of the time series methods in forecasting. Single Moving Average is a forecasting method that is done by collecting a group of observed values, looking for the average value as a forecast for the future period. The result of this forecasting is to predict the number of sales that will occur in the coming month.