CAP4773/CIS6930 Projects in Data Science, Fall 2014 [Review] Overview of Data Science Dr. Daisy Zhe Wang CISE Department University of Florida August 25th 2014 20
Review Overview of Data Science Why Data Science? What is Data Science? What are some prominent examples of Data Science? How to become a Data Scientist? Who are hiring Data Scientists Now? 21
The Dawn of Big Data Google, Yahoo today Core Business: Web Search and Computational advertising Google: 35,000 searches/sec Yahoo! scale: 600 million users per month, 4 billion clicks per day, 25 terabytes of data collected every day Netflix 2007 Movie recommendations 100 million ratings, 500,000 users, 18,000 movies netflix prize Amazon 2003 Product recommendations, reviews 29 million customers, millions of products Word Economic Forum 2011 at Davos Personal data digital data created by and about people represents a new economic asset class, touching all aspects of society. 22
How Big is Your Data? Kilobyte (1000 bytes) Megabyte (1 000 000 bytes) Gigabyte (1 000 000 000 bytes) Terabyte (1 000 000 000 000 bytes) Petabyte (1 000 000 000 000 000 bytes) Exabyte (1 000 000 000 000 000 000 bytes) Zettabyte (1 000 000 000 000 000 000 000 bytes) Yottabyte (1 000 000 000 000 000 000 000 000 bytes) It is not only about volumes! 23
5 Vs of Big Data Raw Data: Volume Change over time: Velocity Data types: Variety Data Quality: Veracity Information for Decision Making: Value 24
Multimodal Data Sources on World Cup Common Twitter ~5M tweets with 244,000 associating images News & Blogs 776 blog posts and associated pictures Facebook 250 posts and associated images Youtube 460 minutes of Videos and Audio Flickr 913 images and associated captions Google Images 1,920 images and associated captions 25
Current Trends Applications has bigger data and need more advanced analysis Example: Web, Corporate documents and Emails Natural Language Processing Example: Social Media Network/Graph Analysis IT Infrastructure moving to Cloud Computing (2006) Parallel Computing, SaaS Elastic Computing pay-as-you-go, scale up/down Data Science arise given this application pull and technology push (2011) 26
27
What is Data Science? 28
Data Science A Definition Data Science is the science which uses computer science, statistics and machine learning, visualization and human-computer interactions to collect, clean, integrate, analyze, visualize, interact with data to create data products. 29
Goal of Data Science Turn data into data products. 30
Data to Data Products Web Text Data Knowledge Bases with Facts & Relationships Twitter Text/Images Real-time Events and News Knowledge bases first-order inference rules and constraints Text Data, Social Media Data Product Review and Consumer Satisfaction Software Log Data Automatic Trouble Shooting Genotype and Phenotype Data common patterns New treatment for Cancer 31
Other Data Products Financial products for investment or retirement funds Legal profession uses e-discovery tool for retrieval and review of legal documents Political campaign management Sports (e.g., Oakland baseball team) Remote Sensing for Environment Monitoring 32
What are some prominent examples of Data Science? 33
Data Products Google Web Search Google Ads News Recommendation Engine Google Maps Currently one of the best if not the best IT company to work for. (Google event on Jan 21/22) 34
Data Products Netflix Personalized Movie Ratings Movie Recommendations Similar Movies Movie Categories (e.g., 80 s movie with a strong female lead, Kung Fu movies) BlockBuster is out of the business 35
Data Products LinkedIn/Facebook People you may know Applications you may like Jobs/Events you might be interested Classifier for bad users and bad content With high accuracy, Facebook can guess whether you are single or married Who does not have LinkedIn/Facebook Account? 36
Data Products Twitter Text Analysis Spam Filter/Similarity Search User Sentiment/Satisfaction/Feedback News Breakout Trend and Topics 200 million users as of 2011, generating over 200 million tweets and handling over 1.6 billion search queries per day 37
Data Products Splunk Degradation, Failure Detection Identify Security Breach Event Monitoring Troubleshoot Tools Cross-platform Event Correlation Founded 2004, IPO in 2012 38
How to become a Data Scientist? 39
The Life of Data (state-of-the-art) Users Interface Collect Clean Integrate Analysis Visualization Data Sources 40
Challenges in Data Science Find Data (Data Collection, Quality) Prepare Data (Noisy, Incomplete, Diverse, Streaming ) Analyze Data (Scalable, Accurate, Real-time, Advanced Methods, Probabilities and Uncertainties...) Represent Analysis Results (i.e. data product) (Story-telling, Interactive, explainable ) 41
Skill Set of a Data Scientist Data Management Data collection, storage, cleaning, filtering, integration Large-scale Parallel Data Processing Parallel computing Statistics and Machine Learning Data modeling, inference, prediction, pattern recognition Interface and Data Visualization HCI design, visualization, story-telling 42
Who are hiring Data Scientists Now? 43
Sexy Job in the next 10 years The sexy job in the next ten years will be The ability to take data to be able to understand it, to process it, to extract value from it, to visualize it, to communicate it that s going to be a hugely important skill. -- Hal Varian, Google Chief Economist, 2009 44
Who s hiring Data Scientist? IT companies: Google, Twitter, Lexis/Nexis, Facebook, Pivotal/EMC Media and Financial sectors Fox, CNN, NYT, Bloomburg, Research: Biology, Medicine, Physics, Psychology, Information office in government and corporations Law firms: e-discovery tools 45
46 Books on Data Science
Additional Reading Pointers Data Science Summit (Strata) (http://www.datascientistsummit.com/ ) Kaggle Competitions (http://www.kaggle.com/) Data Science course at Berkeley (http://datascienc.es/ ) & on Coursera (https://www.coursera.org/course/datasci/ ) 47
Summary Why now: Dawn of Big Data <<- Need for Advanced Analytics and Cloud Computing What is it: Data ->> Data Product, many examples incl. Google, Netflix, Splunk, LinkedIn How to become: Data management, parallel computing and data processing, statistical machine learning, and visualization skills Life of Data Who are hiring: Data Scientists are in great demands, from industry to government to science. 48
Announcements Course Website: http://www.cise.ufl.edu/class/cis6930fa14pro New registration slots will be available @ 4pm TODAY For first year MS students with no data mining background: please first take Introduction to Data Science 49
Next Few Lectures Graph Algorithms and Graph Databases Offline queries: page-rank over Web link structure Online queries: SPARQL (sub-graph matching) over RDF stores Shortest paths (social network transactions) Text and Image Extraction and Retrieval Features Extraction Bag of Words model + Solr indexing More advanced: Entity and event extractions/classifications Knowledge Base Construction, Querying, Integration and Mining General, Health, Ecology, Medical, Rule/Constraint Learning More advanced: Uncertainty Management and reasoning 50