IEEEModelthon 1.0

#IEEEModelthon1_0 #DataScienceHackathon #AIandMLCompetition #RealWorldAI #BusinessProblemSolving #KaggleChallenge #DataScienceModels #ModelDeployment #JordanianUniversityStudents #TeamCompetition #PythonAndR #DataAnalysisTools #PandasEssentials #ScikitLearn #ModelTraining #MLOptimization #SupervisedLearning #HackathonPreparation #AIWorkshopSeries #MachineLearningEvaluation #IEEECS #AI #DataScience #ML #DL #ANN #sklearn #Classification #STEM

Competition Overview:

The first edition of the annual data science hackathon, IEEEModelthon 1.0, aims to engage and inspire those who are passionate about developing data science and artificial intelligence solutions in a realistic business scenarios by engaging them in real-life business problems that need an innovative solutions!

Objectives and Outcomes:

Participating teams will compete over a 2-weeks to develop a data science model based on the given problem description. The main objective of this competition is to put the contestants in a participatory environment that gives them the opportunity to apply their knowledge in a real work environments.

Mainly,  it is a supervised task, and each team should deploy their predictions as a CSV file based on the given problem statement within the Kaggle environment.

Eligibility Criteria: 

• Open to individuals or teams of up to 3 members.
• Participants must be at least 18 years old and be Jordanian undergraduate university students.
• Kaggle’s Competitions rules are applied.
  
  

Prerequisites and Recommended tools:

• Basic understanding of Kaggle's environment.
• Recommended tools: Python, R, Tableau, and relevant libraries (e.g., Pandas, Numpy, Scikit-learn, TensorFlow, etc).
  
  

Training Workshops:

• Pandas Essentials: Data Loading & Storage. 
• Matplotlib Essentials: Exploratory Data Analysis (EDA)
• Scikit-Learn Essentials: Data Preprocessing Techniques
• Machine Learning Essentials: Model Training & Optimization.
  
  

Judging Criteria:

A predefined cost function based on the problem case. (not specified yet).
70% of the evaluation will be based on a test dataset and the rest based on the validation dataset.