smartenit

BACKGROUND

Introduce your business and what you do there.

I’m the founder of a real estate tech company. Our main focus is on estimating the price of the real estate. The first stage of our business is to evaluate the price of apartments in Vienna, Austria. We may expand to other cities later on.

OPPORTUNITY / CHALLENGE

What challenge were you trying to address with smartenit?

I needed a company to develop a network and crawl a data set.

SOLUTION

What was the scope of their involvement?

We have divided the project into three parts. The first stage involved crawling a highly complicated data set from all over the web. We placed an emphasis on our website which lists real estate prices in Vienna, Austria. Our system includes many types of attributes. 

The second phase was dedicated to designing the end-to-end architecture of a deep neural network to use these multi-model attributes not only from tabular features, but also computer vision and natural language processing. The last part is the frontend API that we are now testing for our price evaluation network.

What is the team composition? 

I’ve been in contact with the CTO, project manager, lead data scientist, and an additional 2-3 developers from the team.

How did you come to work with smartenit?

One of my friends suggested smartenit to me. I knew they were very skilled at using deep learning. I contacted them to crow the data and come up with a method to solve a highly complex problem.

What is the status of this engagement?

We started working together in July 2018, and the work is ongoing.

RESULTS & FEEDBACK

What evidence can you share that demonstrates the impact of the engagement?

We just released our first minimum viable product (MVP). After smartenit crawled the data set and designed a network for us, we were able to start testing it on real data. Thanks to their work, we’ve successfully secured some limited contracts with local banks.

None of our competitors have integrated all the multi-model learning capabilities we have. They’re only using tabular features, whereas we have integrated computer vision and text functionalities. 

How did smartenit perform from a project management standpoint?

smartenit is easy to get ahold of and contact. We use Slack to communicate.  

What did you find most impressive about them?

An important factor of success for me was being able to design the entire pipeline. I contacted several other developers beforehand, and none of them had the right combination of skills. smartenit is not only talented at crawling data, but also skilled with machine learning and frontend development. 

smartenit can do it all. They helped us solve a very complicated problem. The team is extremely knowledgeable about deep learning.

Are there any areas they could improve?

I can’t think of anything they need to improve.

Do you have any advice for potential customers?

If you’re interested in creating an entire data pipeline, smartenit will be a very useful partner. It’s very hard to find a team that’s aligned with so many different types of architectures. They offer everything you could need, all in one place.