Agricultural price predictions are an integral component of trade and policy analysis. As the prices of agricultural commodities directly influence the real income of farmers and it also affects the national foreign currency generate. Sesame is highly produced in some tropical and subtropical rain forest Ethiopia region. The thesis is to build a model that can predict market prices of sesame commodity. Based on the complexity of sesame price prediction; the predicting models used for crop are linear regression, support vector machine and neural network models to predict a future price. A data have been taken from the ECX website (www.ecx.com.et) in the interval of January 2013 to March 2019. The total numbers of records selected to the experiments are 5,327 daily prices are used for proposed models. The experimental result had evaluated by RMSE, MSE and CC metrics. We follow six phase CRISP-DM process model for sesame price prediction. The process phase are, business understanding, data understanding, data preparation, modeling, evaluating and deployment.
Table of Contents
- Chapter One
- Introduction
- Background
- Statement of the Problem
- Objective of the Study
- Scope of the Study
- Limitation of the Study
- Significant of the Study
- Thesis Organization
- Chapter Two
- Literature Review and Related Work
- Why Price Prediction?
- Overview of Machine learning
- Frameworks for Building Data Mining
- Related Work
- Summary of Related Work
- Chapter Three
- Methodology
- Data Collection
- Data Analysis
- Data Preprocessing
- Data Transformation
- Attributes Selection Method
- Model Design Methods
- Performance Evaluation Method
- Chapter Four
- Result and Discussion
- Attribute Selection Result
- Experimental Result of Predictive Algorithms
- Performance Evaluation of the Predictive Algorithm
- Chapter Five
- Conclusion and Recommendation
- Conclusion
- Recommendation
Objectives and Key Themes
This thesis aims to predict sesame prices using artificial neural networks. It explores the application of machine learning techniques, particularly neural networks, to analyze historical sesame price data and predict future trends. The research focuses on building a robust and accurate prediction model that can assist stakeholders in making informed decisions.
- Sesame Price Prediction
- Artificial Neural Networks
- Machine Learning
- Data Mining Techniques
- Performance Evaluation of Predictive Models
Chapter Summaries
Chapter One: Introduction provides a background on the importance of sesame price prediction and outlines the research problem, objectives, and scope. It establishes the significance of the study and explains the thesis organization.
Chapter Two: Literature Review and Related Work discusses existing research on price prediction, particularly focusing on machine learning approaches. It reviews various machine learning techniques and data mining frameworks relevant to the study.
Chapter Three: Methodology describes the research methodology used in the thesis. This chapter covers data collection, analysis, preprocessing, transformation, attribute selection, model design, and performance evaluation methods.
Chapter Four: Result and Discussion presents the results of the study and analyzes the performance of the predictive algorithms developed. This chapter evaluates the attribute selection process and the effectiveness of different models in predicting sesame prices.
Keywords
The key focus areas of this thesis are sesame price prediction, artificial neural networks, machine learning, data mining techniques, and performance evaluation. The study explores the application of these concepts to build accurate and reliable models for predicting sesame prices, aiming to provide insights for stakeholders in the sesame market.
- Quote paper
- Endalamaw Gashaw (Author), 2019, Sesame Price Prediction Using Artificial Neural Network, Munich, GRIN Verlag, https://www.grin.com/document/536740
