Many types of machine learning classifiers, not least commonly-used techniques like ensemble models and neural networks, are notoriously difficult to interpret. If the model produces a surprising label for any given case, it’s difficult to answer the question, “why that label, and not one of the others?”. One approach to this dilemma is the technique known as LIME (Local Interpretable Model-Agnostic Explanations). The basic idea is that while for highly non-linear models it’s impossible to give a simple explanation of the relationship between any one variable and the predicted classes at a global level, it might be possible to asses which variables are most influential on the classification at a local level, near the neighborhood of a particular data point. An procedure for doing so is described in this 2016 paper by Ribeiro et al, and implemented in the R…
Original Post: Interpreting machine learning models with the lime package for R
[unable to retrieve full-text content]For Carlos Carcach, Professor & Director, Center for Public Policy at the Escuela Superior de Economía y Negocios (ESEN) in Santa Tecla, El Salvador, gangs are an object of intellectual curiosity and the subject of his research.
Original Post: The Statistics of Gang Violence
[unable to retrieve full-text content]In anticipation of his upcoming conference presentation at Predictive Analytics World for Business Las Vegas, June 3-7, we asked Nishant Sharma, Director, Predictive Analytics at Charter Communications, a few questions about his work in predictive analytics.
Original Post: PAW Interview: Spectrum Cable Lays Fiber with Predictive Analytics – Last Call to Register
[unable to retrieve full-text content]The agenda is live for Predictive Analytics World for Business and Predictive Analytics World for Financial Services Las Vegas — June 3-7, 2018 at Caesars Palace — and we wanted to make sure that you are the first to know.
Original Post: Predictive Analytics World Agendas Are Live—PAW Business & PAW Financial, June in Vegas
[unable to retrieve full-text content]In 2018, there will be only one PAW. Pick Up New Skills at Predictive Analytics World Workshops, Las Vegas, June 2018.
Original Post: Pick Up New Skills – 8 Full-Day Workshops at Predictive Analytics World this June in Vegas
[unable to retrieve full-text content]The e-learning course on profit-driven business analytics presents a toolbox of advanced analytical approaches that support subsequent cost-optimal decision making.
Original Post: New E-learning course: Profit-driven Business Analytics
by Siddarth Ramesh, Data Scientist, Microsoft I’m an R programmer. To me, R has been great for data exploration, transformation, statistical modeling, and visualizations. However, there is a huge community of Data Scientists and Analysts who turn to Python for these tasks. Moreover, both R and Python experts exist in most analytics organizations, and it is important for both languages to coexist. Many times, this means that R coders will develop a workflow in R but then must redesign and recode it in Python for their production systems. If the coder is lucky, this is easy, and the R model can be exported as a serialized object and read into Python. There are packages that do this, such as pmml. Unfortunately, many times, this is more challenging because the production system might demand that the entire end to end workflow is built…
Original Post: How to make Python easier for the R user: revoscalepy
[unable to retrieve full-text content]Trendr.com is a great brand for companies performing any data analysis on trends. Predictive.ly is a perfect brand for a predictive analytics, machine learning, or data science company.
Original Post: 2 Machine Learning-related domain names for sale: Trendr.com and Predictive.ly
[unable to retrieve full-text content]Predictive Analytics World 2018 will be the largest PAW event to date. Don’t miss your chance to speak at Predictive Analytics World’s Mega-Event at Caesars Palace, Las Vegas, June 4-8, 2018. Apply now!
Original Post: Speak at Predictive Analytics World’s 2018 Mega-Event in Las Vegas
[unable to retrieve full-text content]Predictive Analytics World for Business is slated for Oct 29-Nov 2 in New York City. See for yourself precisely how Fortune 500 analytics competitors and other top practitioners deploy predictive modeling and machine learning, and the kind of business results they achieve.
Original Post: Your Complete Guide to Predictive Analytics World – Oct 29-Nov 2 in New York City