Extracting hidden patterns from dates' product data using a machine learning technique

Mohammed Abdullah Al-Hagery

Abstract


Mining in data is an important step for knowledge discovery, which leads to extract new patterns from datasets. It is a widespread methodology that has the capability to help ministries, companies, and experts for diving into the data to find important insights and patterns to help them take suitable decisions. The farmers and marketers of the date product in the production regions lack to discover the most important characteristics of dates types from the economically, healthy, and the type of consumers point of view to achieve the highest profits by choosing the best types and the most consumed. The research objective is to extract interesting patterns from the dates’ product dataset, using Machine Learning, based on association rules generation. This, in turn, will support the farmers, and marketers to discover new features related to the production, consumption, and marketing processes. This research used a real dataset collected from KSA, Qassim region, which is the first region of cultivation of palm, that produces the best types of dates in the Arab region. The data preprocessed and analyzed by the Apriori algorithm. The results show important features and insights related to the health benefits of dates, production, its consumption, consumers types, and marketing. Consequently, these results can be employed, for instance, to encourage individuals to consume dates for their nutritional value and their important health benefits., furthermore, the results encourage producers to focus on the production of preferable types and to improve the marketing policies of the other types.

Keywords


Data Mining, Machine Learning, Association Rules, Data Analysis, Dates Product, Features Extraction



DOI: http://doi.org/10.11591/ijai.v8.i3.pp%25p
Total views : 149 times

Refbacks

  • There are currently no refbacks.


Copyright (c) 2019 Institute of Advanced Engineering and Science

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

View IJAI Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.