Massive Data Made Petite with Hadoop Programming

The core of Apache Hadoop consists of storage known as Hadoop Distributed File System (HDFS) and processing called MapReduce.  Hadoop has the ability to store, manage, and analyze large amounts of data – structured and unstructured quickly, reliably and flexibly and that to at a low-cost.  One of its major benefits include – distributed processing of data local to each node in a cluster.   Its reliability stems from the fact that when a node fails Hadoop processing is re-directed to other nodes in the cluster and data is automatically re-replicated in preparation for future node failures.

Finesse has a team of Big Data and Hadoop experts that can jump in with best in class practices, processes and tools to get you moving in the right direction with your predictive analytics initiative.  Put our experience to test.  Drop us a line and let’s start the conversation.

Problems that can be solved using Predictive Analytics:

It cost 10X more to acquire a new customer Vs keeping an existing one.   A combination of data management and analytics could help you minimize overlooking critical signals regarding customer engagement and customer interaction.   Using Big Data technology allows organizations to build a 360degree customer profile to capture, grow and retain customers.

  • Optimize Marketing and Marketing spend
  • Increase customer loyalty and retention
  • Customer Service and Engagement

Optimize Supply Chain and Improve product quality and service across the supply chain.

Improve insights in localize job markets and matching of job demand and supply

Key Success Examples:

Footfall Analytics.

The Client a consulting company specializing in the implementation of Business Development Initiatives within Automotive Dealerships wanted to the achieve the following:

  • Create an intelligent and robust system for automatic footfall tracking
  • Monitors In-Store traffic movements
  • Provide continuous customer engagement KPIs.
  • Quantify customer engagement KPIs in real-time
  • Manage each stage of purchase cycle and provide quality experience

Our Solution:

  • In-store traffic data collected through beacons
  • Beacon receive wifi signals from customer smartphones
  • Data is encrypted and sent to a central server. Actionable reports are generated

Key Performance Indicators Measured were:

Key Performance Indicators and KPAs

Solutions Implemented

Based on in-store customer’s location data various metrics and customer engagement KPIs were designed. Graph based machine learning and Clustering algorithms were used to identify customer groups. Then a second level algorithms were developed to estimate

Architecture & Technology


Business Benefits & Accuracy Levels

  • Improved the service department’s performance by automated tracking the customer movement
    • Average waiting time
    • Total no of service visits
  • Improved the overall sales engagements by estimating various KPIs
    • Totals no. of customer groups
    • of sales engagement
    • Average sales engagements time
    • of demos and write-ups

Improved customer engagement system helped client to capture 35-40% of floor ups.