A New Domain Specific Scripting Language for Automated Machine Learning Pipeline
Suraya Masrom1, Abdullah Sani Abd Rahman2, Nasiroh Omar3, Norhayati Baharun4
1Suraya Masrom, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Perak Branch, Tapah Campus, Malaysia.
2Abdullah Sani Abd Rahman, Faculty of Science and Information Technology, Universiti Teknologi Petronas, Perak, Malaysia.
3Nasiroh Omar, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Shah Alam, Selangor, Malaysia.
4Norhayati Baharun, Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Perak Branch, Tapah Campus, Malaysia.
Manuscript received on 11 October 2019 | Revised Manuscript received on 20 October 2019 | Manuscript Published on 02 November 2019 | PP: 529-534 | Volume-8 Issue-2S11 September 2019 | Retrieval Number: B10820982S1119/2019©BEIESP | DOI: 10.35940/ijrte.B1082.0982S1119
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper concerns on two difficulties faced by non-experts’ users in the utilization of machine learning; design of the model and the programming task for implementation. From the varieties of the machine learning algorithms, selecting the best model with the best configurations is a critical and complex design issue. In light of this situation, automated machine learning pipeline is highly beneficial. Research has proved that Genetic Programming is highly useful to find the best pipeline of an automated machine learning model. However, in respond to the implementation difficulty, there exists a limited software tool that support easy implementation for automated machine learning based on Genetic Programming. This paper presents the specifications of a domain specific scripting language for the easy development of an automated machine learning with the underlying Genetic Programming. The scripting language has a very minimal characters of codes, hence easier to understand and more concise than the Python programming language.
Keywords: Domain Specific Language, Genetic Programming, Machine Learning, Scripting Language.
Scope of the Article: Machine Learning