Course Code

ΜΔΑ-270

Semester

2nd Semester

ECTS Credits

7,5

Type of Course

Mandatory

Big Data Analytics Applications

Objective

The main objective of this course is to present tangible uses of big data technologies in different sectors spanning form social media and smart cities to healthcare, and education. Different big data techniques will be presented and exploited in the aforementioned sectors, given the particularities, requirements and differentiating aspects of each sector. Emphasis will be put on the analysis both of real-time streaming data and of stored data in each application sector / domain, while business aspects of data analytics and added-value outcomes will also be discussed. Additionally, in the context of this course, students are going to be confronted with practical problems of data analytics in a lab environment, where, given specific datasets for analysis, they will be trained in techniques for exploratory analytics using open-source tools.

 

Course Contents

Geospatial analytics

Geotagging. Location-aware social networks. Combining spatial, temporal and textual data. Applications of Big Data analytics targeting spatial social content. Location-based analytics on Twitter, Flickr, Foursquare.

Web analytics

Opinion mining. Sentiment analysis. Discovering the sentiment in Big Text Corpora. Sentiment analytics on Twitter. Challenges related to short text, noise, informal language. Combining sentiment analysis with geo-location.

Smart cities analytics I

Monitoring the incidence on local economy of hosting different events. Estimation of the outcomes of such events on the local economy (i.e. transport, shops, hotels, restaurants). Monitoring and analyzing the localization of visitors.

Smart cities analytics II

Analysis of energy demand patterns. Situational awareness outcomes. Detected events and their correlation with other events. Consumption patterns by different devices. Environment and congestion prediction by collecting and combining data from different sources (e.g. weather data, congestion, air quality, crowdedness, etc).

Healthcare analytics I

Components of healthcare analytics. Types and sources of healthcare data (e.g. open data, structured EHR data, unstructured clinical notes, genetic data). Methods for selecting, preparing, querying and transforming data for healthcare analytics. Healthcare analytics application with open and closed data.

Healthcare analytics II

Healthcare analytics strategy. Moving from analytics insight to healthcare improvement. Use of pattern evaluation, causes and effects of health in patient populations. Testing hypotheses, build and refine analytic models and interpretation of results relevant to health outcomes. Usability, presentation and visualization of information.

Learning analytics I

Learning analytics fundamentals. Analysis, planning, and deployment of a small learning analytics pilot. Prominent learning analytics tools. Evaluation of current state of learning analytics technologies. Use of open source and proprietary learning analytics tool sets.

Learning analytics II

Learning process analytics for improvement. Using learning analytics for predicting and improving student success. Using Oracle’s BPM Studio 10.3.0 Analytics component. Using indicators for learning process performance monitoring (e.g. elapsed time between activities). Identification and storage of learning process analytics.

Exploratory analytics I

Analytics without concrete problem definition. Data exploration. Discovering interesting properties, patterns, trends in datasets. How to tackle a new dataset. Tools and techniques for exploring data.

Exploratory analytics II

Modeling data in practice. Sampling. Simulations. Pre- and post-processing. Identifying trends with visualizations.

Recommended Readings

  • B. Baesens, “Big Data: Using SMART Big Data, Analytics and Metrics To Make Better Decisions and Improve Performance”, May 2014
  • M. Kleppmann, “Designing Data-Intensive Applications: The Big Ideas Behind Reliable, Scalable, and Maintainable Systems”, January 2016
  • B. Marr, “Big Data: Using SMART Big Data, Analytics and Metrics To Make Better Decisions and Improve Performance”, March 2015
  • A. Chen, R. Zhang, J. Chen: Challenges of Big Data Analytics Applications in Healthcare: The Future of Healthcare, January 2016
  • T. L. Strome: Healthcare Analytics for Quality and Performance Improvement, October 2013
  • P. K Ghavami: Clinical Intelligence: The Big Data Analytics Revolution in Healthcare: A Framework for Clinical and Business Intelligence, April 2014
  • L. B. Madsen: Data-Driven Healthcare: How Analytics and BI are Transforming the Industry, October 2014
  • J.A. Larusson, B. White: Learning Analytics: From Research to Practice, July 2014
  • M. Anderson, C. Gavan: Developing Effective Educational Experiences through Learning Analytics, April 2016
  • Philipp K. Janert: Data Analysis with Open Source Tools: A hands-on guide for programmers and data scientists, O’Reilly Media, November 2010