Tell us about what you do professionally.
I have my own data science consulting firm, Dadrin, that allows me to pursue my passion for helping organizations get smarter with their data. I help organizations with everything from understanding the data they have and how to make a better use of it to building scalable, data-driven solutions using machine learning, natural language processing or computer vision.
How did you hear about DataKind?
I happened to stop by Blue Ridge Foundation when DataKind was still headquartered there and met their Data Engineer, Peter Darche, who told me about DataKind and its mission. I knew immediately that it was something that I wanted to be a part of. I followed up right away with him and Jake Porway, DataKind's Founder and Executive Director, to see what I could do to help.
Tell us about your work with DataKind.
I have been a Data Ambassador on a DataCorps project where we were helping GiveDirectly explore how they can benefit from remote sensing technologies to make there operations more efficient. GiveDirectly identifies some of the poorest households in rural Kenya and Uganda and gives them money via mobile phone transfer. The recipients are free to use the money to pursue their own goals.
GiveDirectly’s goal is to put at least 90 percent of every donated dollar in the hands of the people who need it. To target their services to villages most in need, GiveDirectly uses the roof type of a household as an indicator of their poverty level. For example, families with higher incomes tend to invest in metal roofs instead of thatched roofs.
Their previous DataCorps team created algorithms to analyze satellite images to estimate roof type ratios on those villages and my goal has been to modify them to work with open source technologies and make them more accurate and usable for GiveDirectly.
What inspires you to donate your skills to give back?
Using data science to make the world a better place sounds like a pretty good reason, doesn't it? If you can do this by meeting awesome like-minded people and learning new technologies and skills, it doesn't get any better. That's why as soon as I heard about DataKind, I knew it was a fit for me. I would encourage any data scientist to try it out.
What is one of the most surprising things you’ve learned or seen in working with data?
One of the most surprising things I've learned during my career as a data scientist is that it's more important to ask the right questions than to find the right model. Sometimes people get distracted talking about buzz words such as "big data" or "deep learning" without really understanding what the problem is they're trying to solve for their customers. Very often you do not need complex models or complex data engineering systems to gain insights from data. Learning to ask the right questions and be creative in finding the right answers in the available data are the most valuable skills in a data scientist.
What advice do you have for someone just getting started with data science?
Always listen to your customers, whether they are clients or co-workers in your organization. Make sure that anything you create solves a problem for them. If you build a fancy model and there is no way that it can be used because it takes too many resources to process or its results cannot be easily accessed or interpreted, you will not be providing any value. Always keep in mind the outcome of your work and how people will benefit form it.
When you’re not busy using data science to change the world, what do you like to do in your free time?
Anything outdoors related, especially hiking. I love to get lost in the woods for a few hours to disconnect from the city buzz. The geeky side of me loves reading online about new technologies and trends in the data world as well as attending tech meetups. And I definitely enjoy cooking, especially Paella, the way my Grandpa taught me in my home village of Valencia, Spain.