Presented by: Doaa Mohey Eldin PhD researcher in information Systems Faculty of Computers and Artifical intelligence – Cairo University IEEE Society Member [email protected] 

Agenda • What is Data science? • Why use Data science? • How to use Data Science in real life? • Data science Applications • How to interpret data science model? • Data science Techniques • Data science challenges • Data science trends 2 Data_Science_lecture1_by_Doaa_Mohey 

What is Data Science? • Data Science is – “an informative science that extracts knowledge from various domains. That requires using many algorithms, methods, systems or techniques for scrapping this data and interpret it”. – related to data mining, machine learning, and big data. – Based on using statistics, analysis, or informatics, and their related methods. 3 Data_Science_lecture1_by_Doaa_Mohey 

What is Data Science? • Data Science is – “Data Science is an interdisciplinary field that allows you to extract knowledge from structured or unstructured data.” as a formal definition. – The area of study involves extracting insights from vast amounts of data by the use of various scientific methods, algorithms, and processes. 4 Data_Science_lecture1_by_Doaa_Mohey 

What is Data Science? 5 Computer science/IT Business/ Domain Knowledge Math/ statistics Data Science Data_Science_lecture1_by_Doaa_Mohey 

Why use Data Science? 6 Data_Science_lecture1_by_Doaa_Mohey Why use data science? Effective interpretation of business problems Improve decision making in various domains Powerful predictive systems Managing many users requirements for each system Develop models for real data 

How to use Data Science in Real Life? • Data Science is considered a key of business and real life. It uses for solving prediction problems, analytics problems and risk analysis problems. 7 Data_Science_lecture1_by_Doaa_Mohey Prediction problems Analytics problems Risk problems 

How to use Data Science in Real Life? • It interprets real life applications, Based on various properties. 8 Data_Science_lecture1_by_Doaa_Mohey Characteristics Conditions Techniques Visualization issues Challenges Roles users Scale (large & small) Each application based on various: 

Data Science Applications • Identifying, classification Diseases, and predicting the evolution of diseases progression. • Healthcare recommendations systems. • Predicting incarceration rates. • Business controlling and classifying products. • Automating digital ad placement. • Managing smart environments. • Classifying and interpreting text analysis (such as news) and fraud data. 9 Data_Science_lecture1_by_Doaa_Mohey 

Data Science Applications 10 Data_Science_lecture1_by_Doaa_Mohey 

How to interpret data science model? Define problem Determine model zone Select solution technique Experiment Results 11 Data_Science_lecture1_by_Doaa_Mohey 

Data Science Techniques 12 Data Science Techniques Linear Regression Decision tree Support vector machine Neural networks Classification Logistic regression Data_Science_lecture1_by_Doaa_Mohey 

Data Science Challenges • Big data of high variety information. • Hardness access to data. • Explaining the hardness of data science in interpreting various domains. • Privacy issues. • Lack of significant domain expert. 13 Data_Science_lecture1_by_Doaa_Mohey 

Data Science Trends Data Science Trends Artificial intelligence Internet- of-things Behavioral analytics Machine intelligence Graph analytics 14 Data_Science_lecture1_by_Doaa_Mohey 

15 Data_Science_lecture1_by_Doaa_Mohey