Garuda - Garba Rujukan Digital

Pengembangan Script Forex Trading Otomatis Berdasarkan Indicator Simple Moving Average dengan MQL Programming Abdillah Baradja
TRANSISTOR Elektro dan Informatika Vol 3, No 3: 2018
Publisher : Universitas Islam Sultan Agung

Forex Trading atau pertukaran mata uang asing sudah menjadi bagian kehidupan sehari-hari bagi sebagian masyarakat luar dan dalam negri untuk berinvestasi dalam pergerakan mata uang. Investor forex menggunakan software MetaTrader untuk menganalisa dari setiap perubahan harga mata uang, dengan memperhatikan fluktuasi pasar dapat mengambil keuntungan dari setiap pergerakan mata uang. Proses menganalisa dan memperhatikan fluktuasi pasar ini cukup melelahkan dan membutuhkan waktu lama saat menunggu terjadinya pergerakan arah mata uang. Pada software MetaTrader menyediakan fasilitas untuk menjalankan script yang dibuat dengan MQL Programming untuk melakukan perdagangan berjangka secara otomatis. Penelitian dalam membuat script trading otomatis menggunakan indicator Moving Average untuk menemukan waktu dan harga yang tepat untuk berdagang pada pasar forex. Diharapkan dengan adanya script forex trading otomatis dapat membantu investor kecil atau perorangan agar dapat meningkatkan keuntungan dan menghindari kerugian dalam berdagang pada market forex.

Prediksi Pergerakan Mata Uang dengan Convolutional Neural Network pada Trading Forex: Studi Kasus EUR/USD Abdillah Baradja
Elektriese: Jurnal Sains dan Teknologi Elektro Vol. 12 No. 02 (2022): Artikel Riset Oktober 2022
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/elektriese.v12i02.3627

Prediksi pergerakan pasar di forex trading merupakan tantangan besar karena ketidakstabilan dan sifat non-linear pasar. Kecerdasan Buatan (AI), khususnya pembelajaran mendalam, telah menarik perhatian sebagai alat bantu dalam pengambilan keputusan trading, mengingat keberhasilannya dalam berbagai aplikasi lain. Penelitian ini bertujuan untuk menguji efektivitas jaringan saraf konvolusional (Convolutional Neural Network - CNN) dalam memprediksi pergerakan pasar forex. Penelitian ini menggunakan metode pembelajaran terawasi dengan algoritma propagasi balik untuk melatih CNN. Data yang digunakan diperoleh dari platform MetaTrader, mencakup nilai tukar harian EUR/USD selama dua tahun (2018-2019). CNN dirancang dengan tiga jenis lapisan: konvolusi, sub-sampling, dan terhubung penuh, dengan tujuan untuk mengidentifikasi pola dalam data dan menghasilkan prediksi yang akurat. Hasil eksperimen menunjukkan peningkatan marginal dalam kinerja CNN dibandingkan dengan model neural network lainnya, terutama dalam hal kesalahan prediksi dan ketepatan sasaran. Walaupun demikian, CNN memerlukan waktu dan sumber daya yang lebih banyak untuk pelatihan. CNN menunjukkan potensi dalam meningkatkan akurasi prediksi pergerakan pasar forex dibandingkan dengan model jaringan saraf lainnya, terutama karena kemampuannya dalam preprocessing data dan mengurangi noise. Namun, tantangan terkait waktu dan sumber daya pelatihan perlu ditangani untuk penerapan yang lebih efisien.

Pengembangan Program Pelatihan Digital Marketing untuk Meningkatkan Keberlanjutan UMKM Kuliner di Kota Surakarta, Jawa Tengah Abdillah Baradja; Ramadhian Agus Triono Sudalyo
Jurnal Pustaka Paket (Pusat Akses Kajian Pengabdian Komputer dan Teknik) Vol 1 No 1 (2022): Jurnal Pustaka PAKET
Publisher : Jurnal Pustaka Paket (Pusat Akses Kajian Pengabdian Komputer dan Teknik)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55382/jurnalpustakapaket.v1i1.426

Penelitian ini bertujuan mengembangkan program pelatihan digital marketing untuk meningkatkan keberlanjutan UMKM kuliner di Surakarta. Dengan menggunakan pendekatan kualitatif dan kuantitatif, penelitian ini mengevaluasi efektivitas pelatihan yang mencakup modul SEO, content marketing, dan media sosial. Hasil menunjukkan peningkatan signifikan dalam pemahaman dan aplikasi digital marketing oleh UMKM, berdampak pada visibilitas online dan penjualan. Temuan ini menegaskan pentingnya pelatihan digital marketing dalam mendukung keberlanjutan UMKM di era digital.

Edukasi Teknologi Digital dan Energi Terbarukan sebagai Strategi Penguatan Kapasitas Komunitas Peduli Waduk Jlantah Menuju Pariwisata dan UMKM Berkelanjutan di Karanganyar Ramadhian Agus Triono Sudalyo; Tri Irianto Tjendrowasono; Sukoco Sukoco; Agus Rianto; Abdillah Baradja; Jani Kusanti; Bayu Mukti; Noor Abdul Haris; Frido Oktaviandre
Jurnal Pengabdian Masyarakat: Darma Bakti Teuku Umar Vol 8, No 1 (2026): Januari-Juni
Publisher : Universitas Teuku Umar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35308/baktiku.v8i1.15108

This Community Service (PkM) activity aims to enhance the capacity of the Komunitas Peduli Waduk (KPW) at Jlantah Reservoir, Jatiyoso District, Karanganyar Regency, through digital technology education and renewable energy utilization strategies. The activity was held on March 20, 2025 using a Forum Group Discussion (FGD) method, facilitated by the Surakarta River Basin Authority (BBWS), involving 35 participants from Karangsari and Tlobo Villages. Three main topics were delivered: (1) the use of digital technology for tourism promotion and MSME development via social media, websites, and applications; (2) an introduction to renewable energy power generation including micro-hydro and floating solar power plants; and (3) IoT-based water and soil resource monitoring using ESP32 microcontrollers. Results indicated high participant enthusiasm for technology adoption and a clear need for follow-up technical training to build independent community capacity. The activity successfully fostered multi-stakeholder collaboration among academics, the local community, village government, and BBWS Surakarta toward sustainable development of the Jlantah Reservoir area.

Pengembangan dan Optimasi Kalman Filter Adaptif Multi-Timeframe dalam Kerangka State-Space untuk Prediksi Arah Harga Valuta Asing: Development and Optimization of Multi-Timeframe Adaptive Kalman Filter in State-Space Framework for Foreign Exchange Price Direction Prediction Abdillah Baradja; Sukoco Sukoco; Bayu Mukti
Jurnal Pendidikan Sains dan Komputer Vol. 6 No. 01 (2026): Artikel Riset, February 2026
Publisher : Information Technology and Science (ITScience)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47709/jpsk.v6i01.8007

The foreign exchange market is non-stationary, noisy, and highly sensitive to changes in information, making short-term price direction prediction a significant challenge. Although the Kalman Filter has been widely used within a state-space framework for trend and dynamic parameter estimation, most previous research has focused on statistical accuracy without directly linking it to actual trading performance. This study aims to develop and evaluate an adaptive Kalman Filter-based forex price direction prediction model and empirically test its implications for the performance of algorithmic trading systems. The study uses a quantitative experimental approach, analyzing historical EUR/USD data across the H1, H2, H3, and H4 timeframes over 1 year. The state-space-based Kalman Filter model is implemented in a MetaTrader 5 Expert Advisor and compared with the Moving Average Crossover strategy and the classic Kalman Filter. Evaluations are conducted at the prediction and trading levels using Total Net Profit, Profit Factor, Sharpe Ratio, and Drawdown. The proposed model demonstrates consistently positive performance across all timeframes, with a Profit Factor of 1.39–2.13 and a Sharpe Ratio of up to 5.70, significantly outperforming the technical baseline and the classic Kalman Filter, which exhibit unstable results. The integration of the Kalman Filter approach into an algorithmic trading system improved signal quality and risk efficiency during testing.

COMPARING GAUSSIAN AND DISCRETIZED NAIVE BAYES FOR FOREX TRADING WITH ONNX-INTEGRATED MT5 EXECUTION Abdillah Baradja; Bayu Mukti; Muhamad Fadel Amrullah
Jurnal Teknologi Informasi Mura (JTI) Vol. 18 No. 2 (2026): Jurnal Teknologi Informasi Mura JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i2.3367

Predicting non-stationary, non-normal hourly foreign exchange rates using probability-based classifiers is challenging, and the standard Gaussian assumption for Naive Bayes can be fragile. This study evaluated and compared three Naive Bayes representations for hourly foreign exchange rate prediction to examine the impact of feature discretization. The representations included Gaussian Naive Bayes on continuous indicators, equal-width binned Bernoulli Naive Bayes, and equal-frequency binned Bernoulli Naive Bayes. Relative Strength Index, Average True Range, and Moving Average Convergence Divergence indicators were computed from hourly historical bars for three major currency pairs. The models were trained in Python, exported via the Open Neural Network Exchange, and integrated into MetaTrader 5 for backtesting under a standardized execution gate. Backtests revealed that the quantile-binned equal-frequency model achieved consistent profitability across all three currency pairs, whereas the Gaussian and uniform-binned models demonstrated unstable performance and significant drawdowns. The findings suggested that quantile-based discretization mitigated the impact of outliers and improved classifier robustness in non-stationary market environments.

COMPARING GAUSSIAN AND DISCRETIZED NAIVE BAYES FOR FOREX TRADING WITH ONNX-INTEGRATED MT5 EXECUTION Abdillah Baradja; Bayu Mukti; Muhamad Fadel Amrullah
Jurnal Teknologi Informasi Mura (JTI) Vol. 18 No. 2 (2026): Jurnal Teknologi Informasi Mura JUNI
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jti.v18i2.3367

Predicting non-stationary, non-normal hourly foreign exchange rates using probability-based classifiers is challenging, and the standard Gaussian assumption for Naive Bayes can be fragile. This study evaluated and compared three Naive Bayes representations for hourly foreign exchange rate prediction to examine the impact of feature discretization. The representations included Gaussian Naive Bayes on continuous indicators, equal-width binned Bernoulli Naive Bayes, and equal-frequency binned Bernoulli Naive Bayes. Relative Strength Index, Average True Range, and Moving Average Convergence Divergence indicators were computed from hourly historical bars for three major currency pairs. The models were trained in Python, exported via the Open Neural Network Exchange, and integrated into MetaTrader 5 for backtesting under a standardized execution gate. Backtests revealed that the quantile-binned equal-frequency model achieved consistent profitability across all three currency pairs, whereas the Gaussian and uniform-binned models demonstrated unstable performance and significant drawdowns. The findings suggested that quantile-based discretization mitigated the impact of outliers and improved classifier robustness in non-stationary market environments.

Title

Found 7 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 7 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 7 Documents
Search