BIG DATA ANALYTICS

AIM

This course introduces students to the principles and techniques of Big Data Analytics with applications in Artificial Intelligence (AI). Students will learn how to process, analyze, and derive insights from large-scale datasets using modern big data tools and frameworks. The course covers data storage, distributed computing, real-time analytics, and AI-driven big data applications.

CONTENT

This course contains; Introduction to Big Data & AI Definition of Big Data (Volume, Velocity, Variety, Veracity) Role of Big Data in AI and Machine Learning Big Data vs. Traditional Data Processing Use Cases in AI (Recommendation Systems, Fraud Detection, NLP),Big Data Storage & Processing Hadoop Ecosystem (HDFS, YARN, MapReduce) Apache Spark (RDDs, DataFrames, Spark SQL) Cloud-based Big Data Solutions (AWS EMR, Google BigQuery),NoSQL Databases for AI Introduction to NoSQL (Document, Key-Value, Columnar, Graph) MongoDB for Unstructured Data Cassandra for Scalable AI Applications,Data Ingestion & Preprocessing Data Collection (Web Scraping, APIs, IoT Sensors) ETL (Extract, Transform, Load) Pipelines Handling Missing Data & Feature Engineering at Scale,Machine Learning on Big Data Distributed ML with Spark MLlib Scalable AI Models (Random Forests, Gradient Boosting) Deep Learning on Big Data (TensorFlow/PyTorch on Spark),Real-Time Big Data Analytics Stream Processing (Apache Kafka) Real-time AI Applications (Fraud Detection, Sentiment Analysis),AI-Driven Big Data Applications Recommendation Systems (Collaborative Filtering at Scale) Natural Language Processing (NLP) on Large Text Corpora AI for Predictive Maintenance & Anomaly Detection,Ethics & Challenges in Big Data AI Privacy & Security Concerns Bias & Fairness in AI Models Future Trends (Federated Learning, Edge AI),Final Project (AI + Big Data Application).

1. 1

   Understand the fundamentals of Big Data and its role in AI.

2. 2

   Work with distributed computing frameworks like Apache Spark.

3. 3

   Apply machine learning techniques on large-scale datasets.

4. 4

   Use NoSQL databases (e.g., MongoDB, Cassandra) for unstructured data.

5. 5

   Implement real-time data processing with streaming tools (e.g., Kafka, RedPanda).

6. 6

   Develop AI-powered big data applications (e.g., recommendation systems, predictive analytics).

WEEKLY PLAN

1. WEEK 1

   Introduction to Big Data & AI Definition of Big Data (Volume, Velocity, Variety, Veracity) Role of Big Data in AI and Machine Learning Big Data vs. Traditional Data Processing Use Cases in AI (Recommendation Systems, Fraud Detection, NLP)

2. WEEK 2

   Big Data Storage & Processing Hadoop Ecosystem (HDFS, YARN, MapReduce) Apache Spark (RDDs, DataFrames, Spark SQL) Cloud-based Big Data Solutions (AWS EMR, Google BigQuery)

3. WEEK 3

   NoSQL Databases for AI Introduction to NoSQL (Document, Key-Value, Columnar, Graph) MongoDB for Unstructured Data Cassandra for Scalable AI Applications

4. WEEK 4

   Data Ingestion & Preprocessing Data Collection (Web Scraping, APIs, IoT Sensors) ETL (Extract, Transform, Load) Pipelines Handling Missing Data & Feature Engineering at Scale

5. WEEK 5

   Machine Learning on Big Data Distributed ML with Spark MLlib Scalable AI Models (Random Forests, Gradient Boosting) Deep Learning on Big Data (TensorFlow/PyTorch on Spark)

6. WEEK 6

   Real-Time Big Data Analytics Stream Processing (Apache Kafka) Real-time AI Applications (Fraud Detection, Sentiment Analysis)

7. WEEK 7

   AI-Driven Big Data Applications Recommendation Systems (Collaborative Filtering at Scale) Natural Language Processing (NLP) on Large Text Corpora AI for Predictive Maintenance & Anomaly Detection

8. WEEK 8

   Ethics & Challenges in Big Data AI Privacy & Security Concerns Bias & Fairness in AI Models Future Trends (Federated Learning, Edge AI)

9. WEEK 9

   Final Project (AI + Big Data Application)

ASSESSMENT

• Rate of Midterm Exam to Success50%
• Rate of Final Exam to Success50%

WORKLOAD

READING

• "Big Data: Principles and Best Practices" – Nathan Marz "Learning Spark" – Holden Karau et al. "AI & Big Data in Industry 4.0" – Celestine Iwendi Online: Apache Spark Docs, Google AI Blog, Kaggle Big Data Competitions

TEACHING STAFF

• Assist.Prof. Ahmet KAPLANCOORDINATOR
• Assist.Prof. Ahmet KAPLAN