Slide 1 – Title What Kind of Data Can Be Mined? Subject: Data Mining Presented by: Ayisha Hiba Slide 2 – Introduction Data Mining Data mining is the process of discovering useful patterns and knowledge from large amounts of data. Data can come from different sources. Different types of data require different mining techniques. Major types include: Database data Data warehouse data Transactional data Other types of data Slide 3 – Database Data Database Data Data stored in structured databases can be mined. Databases usually contain tables, rows, and columns. Data mining can discover relationships and patterns in these tables. Example: A college database may contain: Student name Course Marks Attendance Semester Mining can identify: Students with high attendance are more likely to score higher marks. Slide 4 – Data Warehouse Data Warehouse Data A data warehouse stores large amounts of data collected from different sources. It usually contains historical data. It is mainly used for analysis and decision-making. Example: A company may store: Sales information Customer information Product information Yearly sales records Mining can identify: Which products have the highest sales during a particular season. Slide 5 – Transactional Data Transactional Data Transactional data records individual activities or transactions. It is commonly found in shopping, banking, and online systems. Examples: Online purchases ATM transactions Credit card payments Supermarket bills Mining can identify: Customers who buy bread may also frequently buy butter. This is called association analysis. Slide 6 – Other Types of Data Data mining can also be applied to many other forms of data: Text data – documents, emails, articles Web data – websites and user activity Multimedia data – images, audio and video Spatial data – maps and geographical information Time-series data – stock prices, weather records Social media data – posts, comments and interactions Slide 7 – Text Data Text Data Mining Extracts useful information from large collections of text. Used to understand words, topics, opinions and trends. Examples: Customer reviews News articles Emails Social media posts Application: Companies can analyze customer reviews to understand whether customers are satisfied or dissatisfied. Slide 8 – Web and Social Media Data Web Data Information collected from websites and online activities. Social Media Data Posts, comments, likes, shares and user interactions. Applications: Customer behavior analysis Trend detection Personalized recommendations Sentiment analysis Advertising Slide 9 – Multimedia and Spatial Data Multimedia Data Includes: Images Audio Video Example: Mining medical images to help identify diseases. Spatial Data Represents geographical information. Examples: Maps GPS data Satellite images Example: Mining location data to identify traffic patterns. Slide 10 – Time-Series Data Time-Series Data Data collected or recorded over a period of time. The order of data points is i
Slide 1 – Title What Kind of Data Can Be Mined? Subject: Data Mining Presented by: Ayisha Hiba Slide 2 – Introduction Data Mining Data mining is the process of discovering useful patterns and knowledge from large amounts of data. Data can come from different sources. Different types of data require different mining techniques. Major types include: Database data Data warehouse data Transactional data Other types of data Slide 3 – Database Data Database Data Data stored in structured databases can be mined. Databases usually contain tables, rows, and columns. Data mining can discover relationships and patterns in these tables. Example: A college database may contain: Student name Course Marks Attendance Semester Mining can identify: Students with high attendance are more likely to score higher marks. Slide 4 – Data Warehouse Data Warehouse Data A data warehouse stores large amounts of data collected from different sources. It usually contains historical data. It is mainly used for analysis and decision-making. Example: A company may store: Sales information Customer information Product information Yearly sales records Mining can identify: Which products have the highest sales during a particular season. Slide 5 – Transactional Data Transactional Data Transactional data records individual activities or transactions. It is commonly found in shopping, banking, and online systems. Examples: Online purchases ATM transactions Credit card payments Supermarket bills Mining can identify: Customers who buy bread may also frequently buy butter. This is called association analysis. Slide 6 – Other Types of Data Data mining can also be applied to many other forms of data: Text data – documents, emails, articles Web data – websites and user activity Multimedia data – images, audio and video Spatial data – maps and geographical information Time-series data – stock prices, weather records Social media data – posts, comments and interactions Slide 7 – Text Data Text Data Mining Extracts useful information from large collections of text. Used to understand words, topics, opinions and trends. Examples: Customer reviews News articles Emails Social media posts Application: Companies can analyze customer reviews to understand whether customers are satisfied or dissatisfied. Slide 8 – Web and Social Media Data Web Data Information collected from websites and online activities. Social Media Data Posts, comments, likes, shares and user interactions. Applications: Customer behavior analysis Trend detection Personalized recommendations Sentiment analysis Advertising Slide 9 – Multimedia and Spatial Data Multimedia Data Includes: Images Audio Video Example: Mining medical images to help identify diseases. Spatial Data Represents geographical information. Examples: Maps GPS data Satellite images Example: Mining location data to identify traffic patterns. Slide 10 – Time-Series Data Time-Series Data Data collected or recorded over a period of time. The order of data points is i
Created using ChatSlide
This overview covers the essentials of data mining, focusing on its purpose and the extraction of relationships from structured data. It explores transaction analysis to uncover buying patterns and insights from rich data sources like text and social media. Additionally, it delves into advanced data types, including images and audio, and emphasizes the importance of matching data types with appropriate mining techniques for effective forecasting and decision-making.