Data Mining and Analytics Flashcards

Flashcards for Grade 11 Design and Technology, Term 3, 2024-2025, covering data mining, data analytics, and related techniques.

Data Mining

The process of extracting valuable knowledge from large datasets.

Key Components of Data Mining

Artificial Intelligence, Machine Learning, Statistics, Database Systems

Purpose of Data Mining

Transform raw data into understandable, actionable information.

Automatic Pattern Discovery

Systems identify trends and relationships automatically, reducing human bias in data analysis.

Predictive Capabilities

Uses historical data to forecast future trends, helping in decision-making processes.

Actionable Information

Converts complex data into practical insights, enabling data-driven business decisions.

Application of Data Mining in Healthcare (SEHA)

Analyzing historical patient data to identify patterns related to chronic diseases.

Application of Data Mining in Social Media (UAE)

Recommending content aligned with user interactions and showing targeted ads.

Data Analytics

The process of interpreting data to find trends and patterns.

Data Mining

The process of extracting valuable information from a large dataset.

Traditional Data Analysis

A manual or semi-automated process used to examine known variables to answer specific questions.

Descriptive analytics

Focuses on understanding what has happened in the past.

Predictive analytics

Uses historical data to build models that can be used to make predictions about future events.

Prescriptive analytics

Recommending actions that should be taken to achieve desired outcomes.

Traditional Data Analysis

Answer specific questions; data size is small/medium; process is manual or semi-automated; tools are Excel, SPSS.

Data Mining

Discover hidden patterns; data size is large/big data; process is mostly automated; Tools are AI, machine learning, big data tools.

Process of Data Mining

State the problem and formulate the hypothesis, collect the data, preprocess the data, estimate the model, interpret the model and draw conclusions.

Data Preprocessing

Cleaning and preparing raw data before using it for analysis or making models.

Data Cleaning

Fixing or removing wrong, incomplete, or duplicate data.

Data Integration

Combining data from different sources into one.

Data Transformation

Changing data into the right format (e.g., scaling numbers between 0 and 1).

Data Reduction

Making the dataset smaller by keeping only important parts (removing extra/unnecessary data).

Data Discretization

Converting continuous data into small intervals or categories (example: age into 'child', 'teen', 'adult').

Estimate the model

Pick a model based on the problem, feed the cleaned data, check how well the model works and adjust settings.

Interpret model and draw conclusions

See what the model found, understand patterns, make conclusions, take action.

Association

Identifies relationships between items in a dataset.

Classification

identifying which category new data belongs to by learning from data that is already labeled.

Prediction

Uses patterns in existing data to forecast future values or trends.

Clustering

Divides data into groups where items in the same group are similar.

Regression

predict a value based on the relationship between variables.

Artificial Neural Networks (ANNs)

Computing systems inspired by the human brain that learn from data and find complex patterns.

Outlier Detection

Finds data points that are very different from the rest.

Genetic Algorithms

Method of solving problems by mimicking natural evolution.