Applications are invited for a fully funded 3-year PhD studentship (tuition fee waiver + monthly stipend) in the School of Computer Science, Faculty of Science, University of Nottingham Malaysia Campus, under the supervision of Assistant Professor Dr Chen ZhiYuan.
Determining optimal lag time selection function with novel machine learning strategies for better agricultural commodity prices forecasting in Malaysia
• Ministry of Higher Education (Malaysia) (MOHE), Govt. of Malaysia
• Faculty of Science, University of Nottingham Malaysia Campus
The intention of this research is to study and design novel machine learning strategies with optimal lag time selection function to forecast agricultural commodity prices more accurately in order to improve agricultural plantation plan in Malaysia. Due to the increasing large amounts historical data of agricultural commodity prices and the need of performing accurate forecasting of long term direction and short term fluctuations, the solution for time series forecasting has largely shifted from statistical methods to machine learning area. However the formalization of forecasting on agricultural commodity prices problems, the optimal lag time selection function and the role of the forecasting strategy when move from short term fluctuations to long term direction have not been directly studied. Meanwhile, when implementing machine learning techniques, finding optimal parameters of learning algorithm, nonlinearity and avoiding curse of dimensionality are still biggest challenges. In this project, new exogenous and endogenous factors and critical commodities and period of time would be identified. For the optimal lag time selection problem, evolutionary computing strategy, differential evolution has been proposed, which contains 4 main operators: initialization, mutation, recombination and selection. In addition, we propose the gradient based optimization process strategy, the non-linear strategy and kernel-method for tradition machine learning implementation problems. Finally a novel knowledge base of time-series agricultural commodity model incorporating the case based reasoning cycle is presented.
Normally graduate of this University or any other approved higher education institution holding:
i). A Master's degree accepted by the Academic Board;
ii). Other relevant or equivalent qualification with Master's degree accepted by the Senate or competent authority in Malaysia.
English Lanquaqe Requirements:
IELTS: 6.0 (no elements below 5.5)
TOEFL (iBT): 79 (minimum 17 in Writing and Listening, 18 in Reading, 20 in Speaking)
PTE (Academic): 55 (minimum 51)
IELTS and TOEFL test results must be less than 2 years old and all IELTS must be the academic version of the test
Applicants with an MSc/MEng degree in Computer Science, Mathematics, Electrical and Electronic Engineering, or any other related area are welcome to apply. Previous experience in Machine Learning, Pattern Recognition, Time Series data analysis will be an advantage but not a must. The successful candidate is expected to take up the scholarship in January 2019.
For further enquiry on the project and the application procedure, please send your CV together with a cover letter to explain your career aim and why you want to apply, to:
Assistant Professor Dr Chen ZhiYuan
School of Computer Science,
Faculty of Science, The University of Nottingham Malaysia Campus
Selangor Darul Ehsan
Tel: +6 (03) 8924 8141
Posted on 8th November 2018