Sew Lai Ng

Sew Lai Ng

Auto-generated profile, based on publicly available information

Sew Lai Ng

Multimedia University

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 March 2016 in Journal of Quantitative Economics
Verified
Journal Article
Closed access
PDF file
HGHan Hwa Goh
Han Hwa Goh
KTKim Leng Tan
Kim Leng Tan
CKChia Ying Khor
Chia Ying Khor
SNSew Lai Ng
Sew Lai Ng

1 March 2017 in Borsa Istanbul Review
Verified
Journal Article
Open access
SNSew Lai Ng
Sew Lai Ng
WCWen Cheong Chin
Wen Cheong Chin
LCLee Lee Chong
Lee Lee Chong

1 December 2020 in Borsa Istanbul Review
Verified
Journal Article
Open access
SNSew Lai Ng
Sew Lai Ng
WCWen Cheong Chin
Wen Cheong Chin
LCLee Lee Chong
Lee Lee Chong

14 October 2025 in Journal of Informatics and Web Engineering
Verified
Journal Article
Open access
PDF file
MIMuhammad Afif Jazimin Idris
Muhammad Afif Jazimin Idris
SNSew Lai Ng
Sew Lai Ng
Football is the world’s most popular sport, and evaluating the market value of players is crucial for clubs and managers in making informed decisions regarding transfers, contracts, and financial planning. This study aims to develop a predictive model to estimate the market value of football players using machine learning (ML) algorithms and real-life statistics performance data from the top five European leagues such as English Premier League, Italian Serie A, Spanish La Liga, German Bundesliga, and French Ligue 1 between the 2017/18 and 2019/20 seasons. By reviewing past research, various ML methods such as Random Forest, LightGBM, XGBoost, and Gradient Boosting Decision Tree (GBDT) are developed. Data preprocessing techniques, including data cleaning, feature selection, feature encoding, splitting, and standardization, are applied to ensure data quality and consistency. To tune the hyperparameter of the models, RandomizedSearchCV is applied alongside cross validation. The model evaluation is conducted using regression metrics such as mean absolute error (MAE), root mean squared error (RMSE), and coefficient of determination (R²), to determine the most accurate model. The best-performing model is further utilised to analyse the correlation between the features and market value, offering insights into the key features that significantly impact the market value for each position.

14 February 2026 in Journal of Informatics and Web Engineering
Verified
Journal Article
Open access
PDF file
SNSew Lai Ng
Sew Lai Ng
LJLi-Xian Jiao
Li-Xian Jiao
PLPei Qin Lo
Pei Qin Lo
This study aims to identify the best predictive model for analysing online product reviews (OPRs) in the electronics industry, with a secondary focus on leveraging unstructured customer feedback to support product improvement. Using a dataset of 9,675 Oppo mobile phone reviews, this study employs three classification models—Random Forest, Support Vector Machine (SVM) and Logistic Regression–paired with Term Frequency-Inverse Document Frequency (TF-IDF) or bidirectional encoder representation transformer (BERT) as the embedding models to analyse customer sentiment and derive actionable insights. The methodology features a comprehensive analysis pipeline that includes text preprocessing with the Natural Language Toolkit (NLTK), feature extraction using) vectorization and BERT embeddings, and sentiment prediction through various classifiers. The results indicated that BERT was the most effective, achieving the highest accuracy, precision, recall, and F1-score. This superior performance stems from the Random’s ability to handle high-dimensional, sparse data and effectively utilize the weighted word importance provided by TF-IDF, which makes it particularly well suited for sentiment classification tasks involving structured text representations. This study contributes to this field by providing an effective framework for analysing online reviews. This can help businesses understand customer needs for refining product offerings and laying the groundwork for future applications across different product categories.

30 August 2026 in International Journal of Management, Finance and Accounting
Verified
Journal Article
Open access
PDF file
SNSew Lai Ng
Sew Lai Ng
MBMariam Mohamed Abdelwahab Mohamed Badawi
Mariam Mohamed Abdelwahab Mohamed Badawi
RRRuzanna Ab Razak
Ruzanna Ab Razak
SRShaikh Fazlur Rahman
Shaikh Fazlur Rahman
This study examines whether realised range volatility improves multivariate volatility forecasting performance in an emerging equity market setting. A comparison between vector heterogeneous autoregressive models constructed with realised volatility, realised range volatility, and conventional return-based volatility measures is conducted using sectoral data from the Bursa Malaysia. High-frequency data from September 2018 to December 2024 were collected from the financial data provider Bloomberg. The analysis evaluates out-of-sample forecasting accuracy using a set of 5 loss functions, including symmetric (MSE and MAE) and asymmetric (QLIKE) criteria. The outcomes provide compelling and strong evidence that realised range volatility measures deliver superior forecasting performance across sectoral pairs. Realised range volatility models consistently dominate alternatives relying on realised volatility and daily returns, underscoring the significance of efficient and effective volatility measurement in multivariate frameworks. These findings have direct implications for portfolio risk management, regulatory capital assessment, and volatility modelling in emerging markets featured by microstructure frictions and sectoral interdependence.