Home > Research > Researchers > Fahad Al-Qahtani

Supervised by

Fahad Al-Qahtani

Research student

Fahad Al-Qahtani

The Management School Lancaster University Bailrigg Lancaster LA1 4YX

LA1 4YX

United Kingdom

Profile

I am a PhD student in the Department of Management Science at Lancaster University. I hold a master degree in Computer Science from the University of Southern California and I have experience working as a system analyst in the oil and energy sector in the Middle East. My PhD study is in the area of Time Series Forecasting and it is currently sponsored by Saudi Aramco Oil Company under the supervision of Dr. Sven Crone.

Research Interests

My Research interests include machine learning, data mining and time series forecasting.

Current Research

I am currently focusing my research on the utilization of active learning techniques for selecting the most informative examples for training time series forecasting models.

Active learning is an iterative machine learning technique in which the learner has the ability to select only the most informative examples to include in the training data. It has been successfully applied to a variety of data mining applications such as classification and proven to be very effective in achieving greater accuracy with fewer training examples (Cohn et al., 1994, Zhang and Oles, 2000, Tong and Koller, 2002, Guo and Greiner, 2007). Despite its success in data mining, Active Learning has not been directly applied to the problem of training models such as neural network for high frequency time series forecasting and thus offers a very important and still open area of research.

In this study, we propose the question of how Active Learning techniques can be used to select the most informative examples for training models such as neural network that can be used in forecasting high frequency time series. A follow up question would be whether this approach of utilizing Active Learning would actually produce accurate results and less training time compared to the conventional methods of using all training examples passively to train the model.

Supervised By

Dr. Sven Crone, Management Science Department

Qualifications

BS with dual majors in Computer Science and Mathematics, WNEC, USA.

MSc in Computer Science (summa cum laude), USC , USA.

MRes in Management Science, Lancaster University, UK.