Honest thinking about technology decisions. — Page 14

A few weeks ago, I traveled to Sedona Arizona for a few days. While there, I was able to sneak out and get a few sunrise photos. Here's the first of a few

I'm regularly asked about how to get started with big data. My response is always the same: I give them my big data roadmap for success.

Using LIME (Local Interpretable Model-agnostic Explanations) in Python to provide visual explanations of your classification and regression models.

Mathias Lanni highlights how to improve Scrum Marketing Management using smart data collection for better brand outreach.

Guidance for non-technical people on how to ask the right questions to evaluate whether a machine learning model is good enough for the job.

This is the fourth in a series of posts about using Forecasting Time Series data with Prophet. The other parts can be found here: Forecasting Time Series

A brief look back at 2017 and a quick preview of what 2018 looks like for me.

When should deep learning be used? the answer isn't a simple one. The answer depends on the problem, data size and number of other factors.

Stop thinking about big data technologies.  Think of ways to 'analyze, contextualize, internalize' your data instead.

Data and culture must go hand in hand in modern organizations.

As part of a tutorial on Text Analytics and Visualization I just finished  over  on technical blog called Python Data (where I blog about using python for

Using basic Text Analytics and Visualization techniques, keywords can be automatically extracted from text and relationships can be visualized.

When working with data, don't just find the answers to your questions. Keep digging and find new questions to ask.

Rather than blindly follow your a 'successful' company, find ways to incorporate their successes into your organization. Be pragmatic, not dogmatic.

Text Analytics with Python by Dipanjan Sarkar provides an overview of how to use Python to perform text analytics / natural language processing.