Case study

Automated Data Acquisition for a PropTech Innovator

We’ve enhanced our client’s data acquisition strategy with a framework comprising data scraping, validation, normalization, and storage

Key features

  • Online data acquisition from websites and APIs

    Online data acquisition from websites and APIs

  • Data validation with an NLP-powered algorithm

    Data validation with an NLP-powered algorithm

  • Preparation of data for further processing

    Preparation of data for further processing

Industry :
Real Estate
Expertise:
Data & Analytics
Market:
Global
Technologies:

BigQuery / Chromedp / GCP / Go Colly / Golang

Business challenge

Our client provides technology and data science solutions to real estate investors and leading financial institutions worldwide. As the company specializes in advanced data analytics and asset intelligence, its business model relies significantly on digital data acquisition.

Our client’s platform captures massive data sets, consolidates all available information, and transforms unstructured data into business insights. To do this, our client’s company needed to reimagine traditional methods of data acquisition and enhance the processing of large data sets. To that end, they decided to scale the capacity of their data science team with dedicated data acquisition specialists.

Automated Data Acquisition for a PropTech Innovator

Solution delivered

The Intellias team started off by analyzing our client’s current data acquisition strategy to reveal best practices and bottlenecks. Based on the results, we developed a framework as a preliminary solution for acquiring, accumulating, and storing data in a data lake. This framework works for web pages and APIs.

The data acquisition software comprises two types of scraping algorithms: basic and emulated. Based on Chromedp technology, the emulated scraping algorithm imitates the activity of a real user to get relevant and valid data. Next, CSS selectors find and retrieve the needed data from websites.

After that, the data acquisition system triggers a validation algorithm to filter inappropriate data. This algorithm contains a level powered by NLP technology to process the most difficult cases.

Data normalization is performed using Google Maps and Location Services APIs.

Finally, the system stores the data, aggregates it, and molds it into a highly consumable format for further analysis.

Business outcome

As a result of their partnership with Intellias, our client has enhanced their data analytics and asset intelligence, which are a valuable part of their real estate solutions. The automated tools and techniques for data acquisition that Intellias developed help our client optimize their data acquisition processes. They can now acquire a greater volume of data and from a larger number of sources with no need for increased resources.

With automated data acquisition, our client can easily produce insights by turning unstructured data into meaningful data points that have great potential to unlock new business opportunities.

Tell us about your project

I give consent to the processing of my personal data given in the contact form above under the terms and conditions of Intellias Privacy Policy. I want to receive commercial communications and marketing information from Intellias by electronic means of communication (including telephone and e-mail).
* I give consent to the processing of my personal data given in the contact form above under the terms and conditions of Intellias Privacy Policy.

Awards and recognition

logo
logo
logo
logo
logo
logo
logo
logo
logo

Thank you for your message.
We will get back to you shortly.

Thank you for your message.
We will get back to you shortly.