Data Science 101: Part 3 - Data Analysis

In our introductory series on data science fundamentals, Uptake’s data science expert Manny B. explains what data science is, what data scientists do and how businesses can learn and take action from data.

As we learned in part one of our Data Science 101 series, data science is the craft of taking data, learning from that data and deriving actionable insights from those learnings. What is one of the most important parts of data science? You guessed it: data. The results you hope to get from leveraging data science in your business are only as good as the data inputs you start with.

Data science models are trained on historical data. If that data is corrupted or inaccurate, the results you get will be skewed as well. This is especially true of data coming from industrial assets. Industrial data is often messy, as data from equipment can be affected by climate or equipment malfunctions.

Many different factors come into play when analyzing data sources and compiling learnings for the future. In part three of our five-part Data Science 101 series, Manny B. breaks down how velocity, variety, volume and quality all have an impact on how data is put to use.

Play

Check out the rest of our Data Science 101 series or go straight to part four to see the role machine learning plays in the data science workflow.

Watch part 4