Claim Missing Document
Check
Articles

Found 23 Documents
Search

THE EFFECT OF PRODUCT ATTRIBUTES AND CUSTOMER REVIEWS ON SALES PERFORMANCE ON THE TOKOPEDIA E-COMMERCE PLATFORM Aditya Prasetio; Dedy Dwi Prastyo
International Journal of Social Science, Educational, Economics, Agriculture Research and Technology (IJSET) Vol. 5 No. 7 (2026): JUNE
Publisher : RADJA PUBLIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5281/zenodo.22164064

Abstract

This study analyzes the influence of product attributes and customer reviews on sales performance on the Tokopedia e-commerce platform. Data were collected via web scraping from Tokopedia's electronics category (laptops and smartphones), yielding 463 products as the final sample. Product attributes (price, store status, brand clarity, and product description) and customer review indicators (review volume, average star rating, and sentiment score) were used as independent variables, while sales performance (sold count) served as the dependent variable. Sentiment analysis was conducted using a lexicon-based text mining approach with an Indonesian sentiment lexicon. Data analysis was performed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS 4. Results indicate that product attributes have a positive and significant effect on sales performance (β = 0.141, t = 5.706, p < 0.05), and customer reviews have a highly significant effect (β = 0.823, t = 46.768, p < 0.05). Together, both variables explain 76.9% of the variance in sales performance (R² = 0.769). Customer reviews, particularly review volume, are the dominant determinant, while store status is the most influential product attribute indicator.
CoVaR Modelling using QRNN Based on Quantile Regression And Quantile Autoregressive Models with Stochastic Search Variable Selection for LQ45: Pemodelan CoVaR menggunakan QRNN Berdasarkan Regresi Kuantil dan Model Autoregresif Kuantil dengan Pemilihan Variabel Pencarian Stokastik untuk LQ45 Zulfa Wahyu Mardika; Dedy Dwi Prastyo; T. Dwi Ary Widhianingsih
Journal of Data Insights Vol 4 No 1 (2026): Journal of Data Insights
Publisher : Department of Sains Data UNIMUS Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jodi.v4i1.1178

Abstract

Rapid fluctuations in stock prices, particularly during periods of market turmoil, can increase the risk of extreme losses and trigger risk contagion across firms. In risk management practice, Value-at-Risk (VaR) is widely used to measure potential losses at the individual asset or portfolio level. However, VaR is not sufficient to explain how the risk of a given firm changes when another firm or the market is under distress. To address this limitation, Conditional Value-at-Risk (CoVaR) is employed to measure the risk of a firm conditional on extreme conditions affecting another firm or the market, making it more relevant for representing systemic risk contributions and spillover effects among highly liquid stocks such as those included in the LQ45 index. Accordingly, this study focuses on optimizing the input variables of the CoVaR model for the returns of firms included in the LQ45 index by integrating Quantile Regression Neural Network (QRNN) as a nonlinear quantile model and Stochastic Search Variable Selection (SSVS) as a Bayesian variable selection mechanism based on posterior inclusion probability. Within this framework, VaR is first estimated dynamically using Quantile Autoregressive (QAR) and subsequently used as a reference for the distress condition in the CoVaR model. CoVaR is then modelled using QRNN, while the candidate input variables are optimized using SSVS. QRNN is chosen because it is capable of modelling extreme quantiles when the relationship between returns and risk factors is not necessarily linear and tends to vary with market conditions, whereas SSVS is employed to obtain more parsimonious inputs, reduce multicollinearity, mitigate the risk of overfitting, and improve the interpretability of dominant factors.
Banking Market Risk Modelling Using QAR-Based CoVaR with Quantile Regression Alma, Luqyana Zakiya; Prastyo, Dedy Dwi; Rahayu, Santi Puteri; Nugroho, Ari
Jurnal Pendidikan Matematika Vol 9, No 1 (2026): Jurnal Pendidikan Matematika (Kudus)
Publisher : Universitas Islam Negeri Sunan Kudus

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21043/jpmk.v9i1.35180

Abstract

Financial sector stability is essential for economic resilience, particularly in Indonesia’s banking industry. Commonly used risk measures such as Value-at-Risk (VaR) capture individual risk but do not adequately account for systemic interdependence. Existing studies often rely on linear models that are less capable of capturing asymmetric and heavy-tailed return behaviour. This study addresses this gap by developing a Conditional Value-at-Risk (CoVaR) framework based on the Quantile Autoregressive (QAR) approach. This study uses daily closing prices of 15 largest market-cap banking firms listed on the Indonesia Stock Exchange from July 4, 2022, to June 30, 2025. VaR is estimated using QAR, followed by CoVaR estimation through quantile regression, and evaluated using the Kupiec Proportion of Failures (POF) test. The results show that the QAR-based VaR model performs consistently well, with all 15 banks passing the Kupiec test at both the 1% and 5% quantiles, indicating robust tail risk estimation. In contrast, CoVaR results are less stable, with 14 banks passing at the 1% quantile and only 7 at the 5% quantile, suggesting challenges in capturing conditional dependence. Banks such as ARTO and BBHI exhibit stronger systemic spillover effects. This study contributes by integrating QAR into CoVaR modelling and provides insights for systemic risk monitoring in emerging banking markets. Stabilitas sektor keuangan sangat penting dalam menjaga ketahanan ekonomi, khususnya pada industri perbankan di Indonesia. Ukuran risiko yang umum digunakan seperti Value-at-Risk (VaR) mampu menangkap risiko individual, namun belum memadai dalam merepresentasikan keterkaitan sistemik antar institusi. Studi yang ada umumnya masih mengandalkan model linier yang kurang mampu menangkap karakteristik return yang asimetris dan berekor tebal. Penelitian ini mengatasi kesenjangan tersebut dengan mengembangkan kerangka Conditional Value-at-Risk (CoVaR) berbasis pendekatan Quantile Autoregressive (QAR). Penelitian ini menggunakan data harga penutupan harian dari 15 perusahaan perbankan dengan kapitalisasi pasar terbesar yang terdaftar di Bursa Efek Indonesia selama periode 4 Juli 2022 hingga 30 Juni 2025. Estimasi VaR dilakukan menggunakan model QAR, kemudian dilanjutkan dengan estimasi CoVaR melalui regresi kuantil, dengan evaluasi kinerja model menggunakan uji Kupiec Proportion of Failures (POF). Hasil penelitian menunjukkan bahwa model VaR berbasis QAR memiliki kinerja yang konsisten baik, dengan seluruh 15 bank lolos uji Kupiec pada kuantil 1% dan 5%, yang mengindikasikan estimasi risiko ekor yang andal. Sebaliknya, hasil CoVaR menunjukkan stabilitas yang lebih rendah, dengan 14 bank lolos pada kuantil 1% dan hanya 7 bank pada kuantil 5%, yang mengindikasikan adanya tantangan dalam menangkap ketergantungan kondisional. Bank seperti ARTO dan BBHI menunjukkan kontribusi risiko sistemik yang lebih tinggi. Penelitian ini memberikan kontribusi dengan mengintegrasikan QAR ke dalam pemodelan CoVaR serta memberikan implikasi praktis bagi pemantauan risiko sistemik pada pasar perbankan di negara berkembang.