Data Mining Supervised Learning

BSAN 310 University of Kansas

Artificial Intelligence

A computer system that can demonstrate human like intelligence and cognitive functions, such as deduction, patter recognition, and the interpretation of complex data - Jaggia et.al.

Benefits of AI

Automation, reducing human error, eliminating repetitive tasks, infinite availability. accelerated research.

Machine Learning

A branch of AI that enables computers to learn and improve from experience without being explicitly programmed for every task.

Machine Learning Algorithms

Allow systems to identify patterns in data and make predictions or decisions based on that data.

DA

The process of analyzing raw data to make informed decisions.

AI

Machines being able to perform tasks that typically require human intelligence, such as problem solving and decision making.

ML

Training algorithms to learn patterns from data and make decisions based on it.

DL

Utilizes neural networks with many layers to process complex data like images, text, and speech.

GI

Focuses on generating new content, such as text, images, or video.

Data Mining

Describes the process of applying a set of analytical techniques necessary for the development of machine learning and artificial intelligence. Building block of ML and AI.

Data Mining Techniques

Used for data segmentation, pattern recognition, classification, and prediction

Data Mining Process

1. Business Understanding

2. Data Understanding

3. Data Preparation

4. Modeling

5. Evaluation

6. Development

Business Understanding

Assess current inventory of resources, set objectives, and develop project plan: set business success criteria.

Data Understanding

Extract, transform, and load ETL data; verify data quality; visualize and summarize data.

Data Preparartion

Data wrangling, derived features, merging, and aggregating data.

Modeling

Select modeling techniques (e.g, logistic regression, naive Bayes), set parameters, assess models.

Evaluation

Assessment of results, model approval, list of possible actions, decision making.

Deployment

Deploy, monitor and feedback, gain additional insights, and trigger subsequent data mining projects.

Learning from Data

Learn by identifying patterns in datasets

Generalization

Models aim to make accurate predictions on new, unseen data.

Continuous Improvement

Models improve as more data becomes available

Automation of Decisions

Automate tasks that would otherwise require manual intervention

Data Mining is Ideal for:

1. Simplifying complex solutions: Replaces lengthy rules with adaptable algorithms

2. Handling difficult problems: Find solutions where traditional approaches fail

3. Adapting to change: Learn from new data in fluctuating environments

4. Extracting insights: Analyzes large datasets to uncover patters and trend

Applications of Data Mining

Marketing: Predict customer churn, personalize marketing campaigns,

Finance: Detect fraud, algorithmic trading

Healthcare: Diagnose diseases, predict patient outcomes

Retail: Recommend products, optimize inventory

Autonomous Vehicles: Detect objects, navigate roads

Alan Turing (1950)

Introduced the idea of machine intelligence in paper “Computing Machinery and Intelligence,” proposing the Turing Test to measure a machine’s ability to exhibit intelligent behavior.

Arthur Samuel (1959)

Coined the term “Machine Learning” and developed one of the first programs capable of learning to play checkers by improving its strategy over time.