Intoduction to Data Science By Sulav Acharya
- 1. Introduction to Data Science Prepared by : Sulav Acharya Gangadhar Shah
- 2. Objective • Foster interdisciplinary research/education • Promote academia and industry partnership and outreach • Apprehend the field of Data Science impact and important to society • Reflect on its applications, important and advantage
- 3. Contents ▪ Getting started with Data Science ▪ Components of Data Science ▪ Understanding concept of Data Science ▪ Application of Data Science
- 4. Data All Around Lots of data is collected and warehoused • Web data • E-Commerce • Financial transactions • Bank/Credit transaction • Online trading and purchasing • Social Network
- 5. Getting Started with Data Science ▪ Data Science is the study of data to extract meaningful insights for business. ▪ It all combines math and statistics, specialized programming, advance analytics, artificial intelligence(AI) and machine learning with specific subject matter. ▪ It is an area that manage, manipulate, extracts and interprets knowledge from tremendous amount of data ▪ Data science principles apply to all big and small data
- 6. Data Science Real Life Applications Fraud detection ▪ Investigate fraud pattern in past data ▪ Early detection is important ▪ Precision is important ▪ Real-time analytics Recommender System ▪ The ability to offer unique personalize service Netflix recommender system valued at $1B per year Amazon recommender system drives a 20-30% lift in sales annually
- 7. Understanding the concept of Data Science Statistical Analysis Statistics provide the information to educate how things work It is a science of learning from data and of measuring, controlling and communicating uncertainty It is used to design experiments, analyze data, and make informed decision Data science involve the collection, organization, analysis and visualization of large amounts of data Meanwhile, using mathematical model to quantify relationships between variable and outcomes and make predictions based on those relationship Microsoft Edge PDF Document
- 8. Big Data Analytics Big data is any data that is expensive to manage and hard to extract value from • Volume The size of the data • Velocity The latency of data processing relative to growing demand • Variety and Complexity The diversity of sources, format, quality, structure
- 9. Data Mining ▪ Subset of Data Science that involves analyzing large data sets to find patterns and other useful information ▪ It is process of extracting knowledge or insight from large amounts of data using various statistical and computational techniques. ▪ The data can be structured, semi-structured or unstructured and can be stored in various forms such as database and data warehouses. ▪ The primary goal of data mining is to discover hidden patterns and relationships in data that can be used to make informed decisions or predictions.
- 10. Visualization ▪ Data visualization is the process of generating graphical representations like graphs, charts or maps to represent data of information. ▪ Its benefits include communicating your result or findings and monitoring the model's performance.
- 11. Artificial Intelligence ▪ Artificial Intelligence works by simulating human intelligence through the use of algorithms, data and computational power. ▪ AI systems often utilize machine learning algorithms commonly use in data science for prediction modeling and pattern recognition.
- 12. Machine Learning Machine Learning (ML) is a branch of Artificial Intelligence(AI) that use algorithms to automate data analysis, build model that enable computer to learn from data, identify pattern and make decision in minimal human presence. Learning Computer can learn from data sets to perform tasks like analyzing data, categorizing images or predicting image or price fluctuations. Identifying Pattern Computer can identify pattern in large amount of data collection Making Decision Computer can make data-driven recommendations and decision based on input data
- 13. Model Deployment ▪ Model Deployment in data science is the process of integrating a machine learning model into a productive environment so that it take input and produce output.
- 14. Data Governance and Ethics ▪ Data governance is everything you do to ensure data is secure, private , accurate, available and usable. ▪ It is rules, standards and processes defining how data is handled within the company.
- 15. Sample project Microsoft Edge PDF Document