Empowering Data-driven Strategic Decisions for Business Growth

About the Customer

The customer is a real estate listing company based in Santa Clara, California. The organization is 27 years mature and over 1000 people strong with revenue of around $227 Million. The customer wanted to run an analytics program to monetize data to address various business challenges and make data-driven strategic decisions for business growth. Hence, they utilized Brillio’s data expertise to conduct an algorithmic study on various elements of business and then provide appropriate outcomes and recommendations to achieve the organizational goal.

Under the program umbrella Brillio’s performed below projects for the Customer:

1. Leads to sold – Customer ROI Determination
2. Feedback Mining
3. Consumer Prediction Model
4. Customer Churn Analysis

Business Challenge

Being in a highly competitive business, the customer realized that in order to retain the customers while maintaining the profit margins they’ll need to harness the data they’ve collected over 27 years of sheer market dominance. They needed super-accurate data recommendations that help them stay ahead in business despite heavy competition.

For years the customer has been collecting data from various channels like web, application, leads, listing, demographic data, etc. and the data coming from various sources lacked the formatting uniformity and was complicated, to be used to derive useful insights out of. So, they needed a mechanism where after identifying the relevant factors they could be pulled from various sources, harmonized and then could be bestowed to advanced analytics algorithms built by Brillio’s data science team, to address the problem and derive recommendations.

Approach

To help the customer to not only derive insights out of data but also to deal with data and infrastructure challenges Brillio adopted a zoned approach where each zone was handling a particular part of the problem and built individual algorithms for each zone to handle the specific challenge. Not only that, Brillio automated the functioning of all zones to improve the accuracy of the overall recommendation.

To handle the architectural challenges Brillio developed a layered framework of tools and accelerators to pull data from various source systems and various formats. Various tools and accelerators were getting triggered at different layers of the framework. And then the output of one layer was fed as input to the next layer to process it further and then the final output was fed to the next zone.

Solution

Zone 1 – Data Collection 

Data collected from various source systems and fed into the layered framework to make it fit for analytics algorithm consumption in the next zone.

Zone 2 – Data Processing 

Data goes through various sanity checks and corrections through algorithms fed into the zone.

Zone 3 – Data Modelling

Various advanced analytics algorithms built for the problem were fed into this zone and the output of data processing zone was bestowed here for those algorithms to run on.

Zone 4 – Output 

Here, the results of the Data-modelling zone were converted into a consumable format for the customer and hence the recommendations were built.

Business Impact and Benefits

• Saves numerous man-hours that will otherwise be spent on analysing the feedback ( ~300/ week) manually
• Identified that about 11% of consumers transacted on an average
• Determine and understand the segment of customers that derive the most value
• Recover revenue for Opcity by capturing transactions that were not reported
• Safeguards from human errors