Commodity Market Price Analysis and Prediction using Machine Learning Framework
Amanuel Getachew Bulti1, Abhishek Ray2

1Amanuel Getachew Bulti,Electrical and Computer Engineering Department, College of Engineering, Mizan Tepi University/ Tepi, Ethiopia.
2Dr. Abhishek Ray, School of Computer Engineering, Kalinga Institute of Industrial Technology Deemed to be University/ Bhubaneswar, India.

Manuscript received on 02 June 2019 | Revised Manuscript received on 10 June 2019 | Manuscript published on 30 June 2019 | PP: 2822-2828 | Volume-8 Issue-8, June 2019 | Retrieval Number: H7003068819/19©BEIESP
Open Access | Ethics and 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 (

Abstract: Nowadays Ethiopian Market is carried out in a customary way & market drivers are as yet not utilized for a forecast of price of the long run value. In spite of the fact that a lot of market information has been collected all through years by each governmental and non-governmental organizations, nonetheless very little has been done to analyze the data for future value prediction. Moreover, the analysismethods were often manual creating inefficiency in time and quality of market prediction.Analyzing valuable data will show us what the future holds and accelerate the development goalsof the country in the sector. The study examines features of current Ethiopian market attributesto find out the most valuable features for predicting the market price. Eighteen technical indicators aretaken and tested for their individual ability of prediction and redundancy. From the featureselection of commodity market, we have found that features like Stochastic %K, Stochastic %D,Close gain/loss, High, close price, Opening Price, Low, RSI, Ton and Moving AverageConvergence/ divergence (MACD) founded to be in the top ten of individual performanceevaluation. Moreover features namely Stochastic %K, Relative Strength Index (RSI), BollingerBands-Upper, Highest-High, close gain/loss, Simple Moving Average (SMA), Closing price,MACD-Fast, Exponential Moving Average (EMA), MACD-Slow and Low founded to be lessredundant. The study also compares four machine learning frameworks or models for their prediction ability ofEthiopian commodity market price. The outcomes of feature selection were used to compare themodels. Two experiments were conducted; the first was a comparison of the models with 10 fold cross-validation using the feature of high individual predictive ability and less redundancy. Thesecond one was a comparison of models with separate train and test data using features of highindividual predictive ability and less redundancy. From the models (Support Vector Machine(SVM), Artificial Neural Network (ANN), K-Nearest Neighbor (K-NN) and Ensemble Learning)the performance of ANN and Ensemble Learning algorithms are shown to be accurate than SVMand K-NN.
Keyword: Attribute; Feature selection; Machine Learning Algorithms; Price prediction; Technical Indicators.
Scope of the Article: Machine Learning.