BUSI 2400 Lecture Notes - Lecture 2: Market Trend, Pop-Tarts, Big Data
CCR2C9 (attended)
Lama Elnaggar 101019224
Abdullah Ghader 101082405
Emily Abdullah 101046039
Haotian Qi 101084681
Abdullah notes
●data:
○ •Digital (numbers only; including binary, decimal and others)
○ •Textual (letters and numbers – alphanumeric)
○ •Visual
○ •Aural
○ •Other sensory (touch, smell)
●What does data look like:
○ If it is structured as a database we can predict a row by column format
○ If it is unstructured it will be without organization
●What is Big data?
○ Data that cannot be measured with traditional data processing applications
●Video
○ Vision recognition brings more data
○ Smart object go online
○ New forms of scientific data
○ Volume: the sheer amount of Big Data is almost unfathomable
○ Velocity: The speed at which the big data is generated
○ Variety: the sources of Big Data are broad and growing every day
○ Big data can lead you to ignore primitive data
■ Much of retail transactions were not processed
■ Hospital Services were also neglected
●“ If you know what questions to ask of your transactional cash register data, which fits nicely
into a relational database, you probably don't have a Big Data problem.”
●Context: All context and data is Connected
●Data exhaust: Much produced data is ignored
●Benefits of Big data: Small/Little data is expensive – it needs to be managed Ex.
data like your credit card statement or your phone bill
●Correlation vs. Causation
○ Correlation: are Storms and Pop tarts related?
○ Causation: do Storms cause a craving for pop tarts?
●Who owns the Data?
○ Are you allowed to access your data?
●Big data has value
○ Ex. Physicians should inform patients with their Big data
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Digital (numbers only; including binary, decimal and others) If it is structured as a database we can predict a row by column format. If it is unstructured it will be without organization. Data that cannot be measured with traditional data processing applications. Volume: the sheer amount of big data is almost unfathomable. Velocity: the speed at which the big data is generated. Variety: the sources of big data are broad and growing every day. Big data can lead you to ignore primitive data. Much of retail transactions were not processed. If you know what questions to ask of your transactional cash register data, which fits nicely into a relational database, you probably don"t have a big data problem. Context: all context and data is connected. Data exhaust: much produced data is ignored. Benefits of big data: small/little data is expensive it needs to be managed ex. data like your credit card statement or your phone bill.