Home page / Cases / Entity Recognition

Entity Recognition

The online marketplace for cars wanted to improve search for users by adding full-text and voice search, as well as advanced search with specific options. We built a system application using Machine Learning and NLP methods to process text queries, and the Google Cloud Speech API to process audio queries. This helped greatly improve the user experience by providing a more intuitive and efficient search option for them.

Data Science

2x

faster service

15%

CX boost

About the client

The leading online car marketplace serving private sellers and over 10,000 dealers across the United States, connecting buyers with all makes and models of vehicles for sale in close proximity.

Tech stack

Python

Pandas

Pyspark

TensorFlow

PostgreSQL

Hadoop

Challenges & solutions

Challenge

To add a full-text and voice search for users across the entire platform.

Solution

Server application as an optimal solution for the marketplace.

Challenge

To transform the search into an advanced search with a specific structured view according to specific parameters: condition, mileage, price, body style, make, model, seller type, transmission, exterior color, etc.

Solution

Tool which in the process of receiving user queries automatically divides them into two corresponding groups:
- Text Queries - natural language processing #NLP using Machine Learning models. The text is cleaned up, the key elements of the query are identified, and the final result is rendered. The average processing speed is less than 100 ms;
- Audio Queries - natural language processing NLP using the Google Cloud Speech API application.

Technically proficient and solution-oriented.

Brian Bowman

President Carsoup, automotive online marketplace

The way we deal with your task and help achieve results

Step 1 of 5

Free consultation

It's a good time to get info about each other, share values and discuss your project in detail. We will advise you on a solution and try to help to understand if we are a perfect match for you.

Step 2 of 5

Discovering and feasibility analysis

One of our core values is flexibility, hence we work with either one page high level requirements or with a full pack of tech docs.

In Data Science, there are numerous models and approaches, so at this stage we perform a set of interviews in order to define project objectives. We elaborate and discuss a set of hypotheses and assumptions. We create solution architecture, a project plan, and a list of insights or features that we have to achieve.

Step 3 of 5

Solution development

The work starts with data gathering, data cleaning and analysis. Feature engineering helps to determine your target variable and build several models for the initial review. Further modeling requires validating results and selecting models for the further development. Ultimately, we interpret the results. Nevertheless, data modeling is about a process that requires lots of back and forth iterations. We are result focused, as it’s one of our core values as well.

Step 4 of 5

Solution delivery

Data Science solutions can be a list of insights or a variety of different models that consume data and return results. Though we have over 15 years of expertise in data engineering, we expect client’s participation in the project. While modeling, we provide midterm results so you can always see where we are and provide us with feedback. By the way, a high-level of communication is also our core value.

Step 5 of 5

Support and continuous improvement

We understand how crucial the solutions that we code for our clients are! Our goal is to build long-term relations, so we provide guarantees and support agreements. What is more, we are always happy to assist with further developments and statistics show that for us, 97% of our clients return to us with new projects.

Success stories

Check out a few case studies that show why DATAFOREST will meet your business needs.

All Success Stories

System integrations

Data Scraping

Business process automation

Data Science

Data parsing

We helped a law consulting company create a unique instrument to collect and store data from millions of pages from 5 different court sites. The scraped information included PDF, Word, JPG, and other files. The scripts were automated, so the collected files were updated when information changed.

14.8 mln

pages processed daily

43 sec

updates checking

Sebastian Torrealba

CEO, Co-Founder DeepIA, Software for the Digital Transformation

View case study

These guys are fully dedicated to their client's success and go the extra mile to ensure things are done right.

Data-driven marketing

We created a solution that helped optimize the customer base to get the most out of the customer data. This solution notifies the client about the services/goods, which they would likely buy, according to the gathered information.

20%

sales growth

200%

traffic boost

Jeremy Groves

CEO ThinkDigital, Digital and Advertising Agency

View case study

They developed solutions that brought value to our business.

Web app for dropshippers

The Client wanted to create a web app for people who sell products online (dropshippers) to show them the most popular products and calculate the potential profits. DATAFOREST designed and built the web app from scratch, creating high-load scraping algorithms to extract data from different eCommerce marketplaces, developing AI algorithms to calculate profits, and integrating the payment system with various functionalities.

100k+

hourly users

1,5 mln+

Shopify stores

Josef G.

CEO, Founder Software Development Agency

View case study

If we experience any problems, they come back to us with good recommendations on how the project can be improved.

DevOps Experience

The ML startup faced high costs during its growth for a data-driven platform infrastructure that processes around 30 TB per month and stores raw data for 12 months on AWS. We reduced the monthly cost from $75,000 to $22,000 and achieved 30% performance over SLA.

2k+

QPS performance

70%

cost reduction