Sesame Price Prediction Using Artificial Neural Network

Table of Contents

1. Introduction

1.1. Background

1.2. Statement of the Problem

1.2.1. Research Questions

1.3. Objective of the Study

1.3.1. General Objective

1.3.2. Specific Objective

1.4. Scope of the Study

1.5. Limitation of the Study

1.6. Significant of the Study

1.7. Thesis Organization

2. Literature Review and Related Work

2.1. Price Prediction

2.2. Why Price Prediction?

2.3. Overview of Machine learning

2.3.1. Supervised Learning

2.3.2. Unsupervised Learning

2.3.3. Reinforcement Learning

2.4. Frameworks for Building Data Mining

2.4.1. Knowledge Discovery Databases (KDD)

2.4.2. Cross-Industry Standard Process for Data Mining

2.4.3. SEMMA (Sample, Explore, Modify, Model, Assess)

2.5. Related Work

2.5.1. Summary of Related Work

3. Methodology

3.1. General Framework of Proposed Architecture

3.2. Data Collection

3.3. Data Analysis

3.4. Data Preprocessing

3.5. Data Transformation

3.6. Attributes Selection Method

3.6.1. Correlation-based Feature Selection (CFS)

3.6.2. Relief Attribute Evaluation

3.7. Model Design Methods

3.7.1. Linear Regression

3.7.2. Support Vector Machine

3.7.3. Neural Network

3.8. Performance Evaluation Method

3.8.1. Correlation Coefficient (CC)

3.8.2. Mean Absolute Error (MAE)

3.8.3. Root Mean-Squared Error (RMSE)

4. Result and Discussion

4.1. Attribute Selection Result

4.2. Experimental Result of Predictive Algorithms

4.2.1. Predicting of Sesame Closing Price Using Linear Regression

4.2.2. Predicting of Sesame Price Using Support Vector Machine

4.2.3. Predicting of Sesame Price using Neural Network

4.3. Performance Evaluation of the Predictive Algorithm

4.3.1. 10 Fold Cross Validation

4.3.2. Percentage Split Validation (70%Training and 30% Testing)

5. Conclusion and Recommendation

5.1. Conclusion

5.2. Recommendation

Research Objectives and Themes

The primary objective of this thesis is to design and develop a predictive model for the Ethiopian sesame market to forecast future prices based on historical data. By analyzing factors such as trade date, quantity, production year, and various price metrics (opening, closing, min, and max), the study aims to provide decision support for farmers, traders, and policymakers to mitigate market risks and improve economic planning.

• Data mining and predictive modeling in the agricultural sector.
• Application of machine learning algorithms (Linear Regression, Support Vector Machine, and Neural Network).
• Feature selection methodologies for high-dimensional agricultural datasets.
• Performance benchmarking using 10-fold cross-validation and percentage split validation.

Excerpt from the Book

Summary of Chapters

1. Introduction: Discusses the significance of sesame as a key export commodity for Ethiopia and defines the research objective of building a price prediction model.

2. Literature Review and Related Work: Reviews existing studies on agricultural commodity price prediction using various data mining techniques and frameworks.

3. Methodology: Details the architecture, data collection, preprocessing, feature selection methods, and the specific machine learning algorithms used for prediction.

4. Result and Discussion: Presents the experimental results of attribute selection and compares the accuracy of the predictive models using various metrics.

5. Conclusion and Recommendation: Summarizes the findings, highlighting the superior performance of the neural network model, and suggests areas for future research.

Keywords

Price prediction, linear Regression, Support Vector Machine, Neural Network, ECX, Sesame, Ethiopia, Data Mining, Agriculture, Machine Learning, Feature Selection, Forecasting, 10-fold Cross Validation, RMSE, Correlation Coefficient

Frequently Asked Questions

What is the primary goal of this research?

The study aims to build a predictive model to forecast future market prices for sesame in Ethiopia to support better decision-making for farmers and traders.

What central themes are covered?

The work focuses on agricultural price forecasting, the application of data mining techniques, and the comparative performance of supervised learning algorithms.

Which algorithms are utilized?

The research compares three main algorithms: Linear Regression, Support Vector Machine (SVM), and Artificial Neural Network (ANN).

What is the methodology used?

The study follows a five-phase design science process: problem awareness, suggestion, development, evaluation, and conclusion, utilizing data from the Ethiopian Commodity Exchange (ECX).

What does the main body address?

It covers data collection from seven major markets, preprocessing of 5,327 records, attribute selection via CFS and Relief methods, and performance benchmarking of the chosen models.

Which keywords define this work?

Key terms include Price prediction, Sesame, Machine Learning, Neural Network, Linear Regression, SVM, and Ethiopian Commodity Exchange (ECX).

Why are environmental factors suggested for future work?

The author recommends including factors like annual rainfall and global market demand to further increase the model's accuracy and robustness.

How were the models evaluated?

Models were evaluated using statistical metrics including Correlation Coefficient (CC), Mean Absolute Error (MAE), and Root Mean-Squared Error (RMSE), tested via 10-fold cross-validation and a 70/30 percentage split.