Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimasi Algoritma XGBoost Berbasis SMOTE untuk Mengidentifikasi Faktor Logistik Pemicu Pembatalan Pesanan E-commerce Arif Fitra Setyawan; Thomas Tri Wibowo; Intan Laily Muflikhah; Muhammad Bhayu Bramantyo
Elkom: Jurnal Elektronika dan Komputer Vol. 19 No. 1 (2026): Juli : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v19i1.3913

Abstract

Unilateral order cancellation by consumers is a major operational challenge in the Indonesian e-commerce industry, directly impacting supply chain inefficiency and inflating logistics costs. Computational modeling to predict this risk often faces hurdles such as class imbalance and vulnerability to data leakage. This study proposes an optimization of the Extreme Gradient Boosting (XGBoost) algorithm integrated with the Synthetic Minority Over-sampling Technique (SMOTE) using a multi-scenario feature analysis approach. The dataset used comprises real transaction records from a major e-commerce platform. Experiments were designed in two scenarios: Scenario 1 included all transactional features, while Scenario 2 excluded the dominant financial feature (Total Pembayaran) to test the model's pure dependency on pre-finalization variables. The test results showed that Scenario 1 yielded a pseudo-accuracy of 99.50% due to data leakage. After reconstruction in Scenario 2, the SMOTE-based XGBoost model produced a stable real performance with an Accuracy Score of 83.96% and an Area Under ROC (AUC) of 86,98%. Through Feature Importance analysis, this study successfully revealed that pure logistics factors, specifically "Ongkos Kirim Dibayar oleh Pembeli" (Shipping Fee Paid by Buyer) with an absolute importance weight of 77.10%, serve as the primary predictor and driver behind consumer order cancellations. These findings provide tactical contributions for e-commerce decision-makers in formulating shipping cost strategies and mitigating early operational risks.
Multipath Channel Analysis at 30 GHz for 6G Wireless Networks Based on BER Performance Reni Dyah Wahyuningrum; Thomas Tri Wibowo; Ida Udlhiya; Rizkha Ajeng Rochmatika; Devi Yesitasari; faizah faizah
Journal of Telecommunication Electronics and Control Engineering (JTECE) Vol 8 No 2 (2026): Journal of Telecommunication, Electronics, and Control Engineering (JTECE) (In Pr
Publisher : LPPM INSTITUT TEKNOLOGI TELKOM PURWOKERTO

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/jtece.v8i2.2151

Abstract

The development of sixth-generation (6G) wireless networks has encouraged the utilization of millimeter-wave (mmWave) spectrum to support extremely high data rates and network capacity. However, signal propagation at mmWave frequencies is highly susceptible to multipath effects and severe path loss, particularly under Non-Line-of-Sight (NLOS) conditions. This study analyzes the characteristics of a 30 GHz multipath channel using the NYUSIM channel simulator and evaluates its impact on Bit Error Rate (BER) performance. Simulations were conducted in an Urban Microcell (UMi) NLOS scenario with a bandwidth of 400 MHz, employing 64-QAM modulation, Orthogonal Frequency Division Multiplexing (OFDM), and a rate-1/2 Convolutional Code. Channel characterization results indicate a path loss of 127 dB, an average received power of −96.1 dBm, and an RMS delay spread of 14.6 ns. Furthermore, the Angle of Arrival (AOA) and Angle of Departure (AOD) analyses reveal that signal propagation is dominated by reflected paths due to the absence of a direct Line-of-Sight (LOS) component. BER performance evaluation shows that increasing the Signal-to-Noise Ratio (SNR) from 0 dB to 14 dB reduces the BER from approximately 4.8 × 10⁻¹ to 9 × 10⁻³. At an SNR of 16 dB, the system achieves a BER below 10⁻³, indicating a substantial improvement in transmission reliability. The results demonstrate that the combination of OFDM and Convolutional Coding effectively mitigates the effects of multipath fading in mmWave channels, making it a promising solution for future 6G wireless communication systems operating at 30 GHz.