Tags » Data Mining

Data-data-data: why and how to use data

Data are generated everywhere, and about everything. With 2.5 quintillion bytes of data generated per day, we create data like our cells create carbon dioxide – relentlessly. 491 more words


Peter Galison | Cultures of Collection and the State of Secrecy

In this lecture, Peter Galison will contrast two moments in the long history of surveillance―two moments that have and are reshaping the self. The first, set in 1915, is about the Freudian self and its emergence in the midst of the massive press and postal censorship of World War I. 308 more words

Fall 2015

Product recommendation

INPUT: Transaction list of {DateTime, Customer, Item}

OUTPUT:  Set of {Customer, Recommended Items}

METHOD: Collaborative Filtering algorithms.


Data Mining

Outlier detection

INPUT: Transaction list of {DateTime, Value}

OUTPUT: List of values which are outliers

METHOD: Regression & Gaussian process


Data Mining

Customer segmentation

INPUT: transaction list of  {date, customer, value}

OUTPUT: 4 segments of customer
– Best customer: high value, high using frequency, last visit is near. 55 more words

Data Mining

Open Source Windows May Not Be that Big a Long Shot After All — Fortune

Here’s a burning question for the tech universe: Could Microsoft, which built its Windows cash cow on proprietary or closed-source software, reverse course and open-source Windows itself?

43 more words
Data Mining

#Windows #10 - security and #privacy

I don’t normally review operating systems – I’m not that much of a geek – but I’ve decided to make an except for Windows 10. In a series of posts aimed at the ordinary user, I hope to answer the question – is this free upgrade worth it? 1,264 more words