Analysis of Global Food Crisis Test phase, srs, design phase and source code final deliverable
Category
Information Mining and Retrieval.
Abstract/Introduction
Project Introduction:
The world faces a global hunger crisis of unprecedented proportions. In just few years, the number of people facing, or at risk of, acute food insecurity increased from 135 million in 53 countries pre-pandemic, to 345 million in 82 countries today. For the analysis of global food crisis, you have to process the kaggle dataset containing information about food prices, meat prices, dairy prices, cereal prices, oil prices, and sugar prices. This data is of utmost importance to researchers as it will help inform their work on finding solutions to this potential crisis.
You have to implement the latest AI algorithms for achieving the highest accuracy and precision for this issue. The famous AI algorithms are Naive Bayes, Apriori, Association Rule Mining, Decision Trees, Support Vector Machines, Logistic Regression, C4.5, CART, CNN, RSNET and many more. You must know the valid reasons for choosing specific algorithms over others according to the data needs.
Domain Introduction:
The project is related to the information mining and retrieval. An algorithm in this area is a set of heuristics and calculations that creates a model from data. To create a model, the algorithm first analyzes the data you provide, looking for specific types of patterns or trends. The algorithm uses the results of this analysis over many iterations to find the optimal parameters for creating the mining model. These parameters are then applied across the entire data set to extract actionable patterns and detailed statistics.
Choosing Right Algorithms:
Choosing the best algorithm to use for a specific analytical task can be a challenge. While you can use different algorithms to perform the same task, each algorithm produces a different result, and some algorithms can produce more than one type of result. For example, you can use the Decision Trees algorithm not only for prediction, but also as a way to reduce the number of columns in a dataset, because the decision tree can identify columns that do not affect the final mining model. There is no reason that you should be limited to one algorithm in your solutions. Experienced analysts will sometimes use one algorithm to determine the most effective inputs (that is, variables), and then apply a different algorithm to predict a specific outcome based on that data. Data Mining lets you build multiple models on a single mining structure, so within a single data mining solution you could use a clustering algorithm, a decision trees model, and a Naïve Bayes model to get different views on your data. You might also use multiple algorithms within a single solution to perform separate tasks: for example, you could use regression to obtain financial forecasts, and use a neural network algorithm to perform an analysis of factors that influence forecasts.
Functional Requirements:
Your system must fulfill the following requirements:
- Find the general trend in food prices over time.
- Analyse the significant relationship between different food prices.
- Analyse the impact of increased oil prices on the prices of other food items.
- Estimate the economic impact of a potential global food crisis over time.
- Develop policies to mitigate the impact of a potential global food crisis.
Tools:
The following tools can be used for developing the above project:
- Anaconda
- Numpy
- Jupiter Lab.
Dataset Download Link:
You can download the dataset from: https://www.kaggle.com/datasets/thedevastator/food-prices-year-by-year
References: https://learn.microsoft.com/en-us/analysis-services/data-mining/data-mining-algorithmsanalysis-services-data-mining?view=asallproducts-allversions https://www.kaggle.com/datasets/thedevastator/food-prices-year-by-year
Supervisor:
Name: Anum Liaquat
