Forget Google: Is This The Best Company To Work For?

Anyone who isn't familiar with Etsy, an e-commerce site dedicated to selling homemade and vintage items, ought to check out the site immediately. Etsy does a superb job of providing products that cater to and match individual taste; moreover, the site provides a customized user experience to fit personal preference.

Basically, Etsy takes on the often-annoying chore of sifting through items that might catch your eye.

For that, you can thank Diane Hu, a data scientist for Etsy; she has the codes, and she’s not afraid to use them. Diane and her team are on the brink of bringing a unique homepage, tailored by past favorites and purchases, to every person that shops on Etsy. So, what does it really take to construct a site that has 30+ million registered users? Take a look into Diane’s day below to find out.

9 a.m.: Begrudgingly wake up. Fire up my beloved WNYC app on my phone to listen to NPR (The Brian Lehrer Show is one of my favorites) while I get ready for the day. This helps me wake up.

10 a.m.: The subway stop is right next to my house, thank goodness. Hop on the F-train in Carroll Gardens and ride three stops into Dumbo, Brooklyn.

10:15 a.m.: Stop by The Steel Cart — a cute, breakfast food truck — on the way from the subway station to work. They are strategically placed so that the smell of their grits, bacon, and kale (my favorite) is seemingly unavoidable, no matter which route I take.

10:30 a.m.: Our data science team has a weekly Monday morning planning meeting. For me, I'll be spending most of my time this week collaborating with our homepage team who is experimenting with improving the Etsy homepage. The most exciting part is that the new version will be personalized — each of our 40 million users will log into Etsy and be exposed to personalized content tailored to each's individual taste, based on past favorites and purchases. These personalized recommendations were generated by our team using various machine learning and data mining algorithms.

11 a.m.: One of many coffee runs throughout the day. My next-desk neighbor and I grab a re-useable Etsy coffee jar and go to Almondine, a nearby French bakery.

12 p.m.: My weekly meeting with my manager. We take a walk around the neighborhood while we talk about workplace relations, ideas, and projects.

1 p.m.: I run over to the little deli next door to get a salad and some chicken wings. If it were a Tuesday or Thursday, I would be grabbing lunch at Eatsy, our lunch program where local restaurants cater a healthy and delicious multi-course meal.

1:30 p.m.: Some belly rubs for Hoover, a sweet beagle mix! Another coffee/tea run.

2 p.m.: Finally, time to do some work! The rest of the day is spent coding. Most of the code I'm working on right now deals with getting personalized user, item, and shop recommendations integrated into the new homepage.

2:30 p.m.: Beanie, an adorable diva of a Corgi (we call her Queen Bea), comes sauntering over to our team's cluster. I can't resist giving her some belly rubs, too.

5 p.m.: We recently had a paper on our recommendation systems work get accepted to an academic conference called KDD (Knowledge Discovery & Data Mining) — one of the top conferences in the data science field. Today just happens to be the camera-ready deadline. I spend some time editing and polishing up our paper before submitting it for publication.

7 p.m.: Head back to the subway to go home. Stop by "Under the Archway" (literally, under one of the arches of the Manhattan Bridge) where a huge crowd has gathered to watch USA play Ghana in the World Cup on a giant screen. I'm not really into soccer, but the cheers were so loud that I had to see what was going on.

8 p.m.: It's my husband's night to cook. He makes a delicious asparagus pasta from our Quinciple box this week.

9 p.m.: Eat dinner together in front of the television. We're watching old seasons of Scrubs on Netflix. I edit photos from my last engagement shoot, and answer some emails for my photography business.

12 - 1 a.m.: Get ready for bed. Yes, we go to sleep late. Old habits (from our grad school days) die hard!