GRIDMINE - USE CASES

GridMine is designed to support both Batch and Stream processing. We enable this through support for multiple analytics frameworks and tools including Hadoop, Spark and Storm.

The use cases that can be supported cover practically the entire gamut of processing types such as machine learning, anomaly detection, statistical and predictive analytics. And application types such as log analysis, web indexing, data warehousing, machine learning, financial analysis, scientific simulation, and bioinformatics.

Government Cloud Marketplace

We built and maintain the underlying platform for New Zealand Governments procurement market place. Solution is hosted on Kubernetes and meets strict operational and security compliance guidelines. We provide ongoing support, 24/7 monitoring and maintenance.


Technologies: Kubernetes, ZeroMQ, MongoDB, MariaDB, ArgoCD, Jenkins etc.

Customer Location: New Zealand

predictive analytics
machine learning

AI & ML Hub

For a leading Data Science and AI consultancy we implemented a combined Big Data and Kubernetes cluster which brought together their Data Science as Service Platform. We also implemented the solution on customer sites and provided the ongoing maintenance and support.


Technologies: Kubernetes, Hadoop Ecosystem tools, Jupyter, NiFi, Elasticsearch, Kibana etc.

Customer Location: Switzerland

Realtime Transaction Analytics Platform

For a leading bank we built the infrastructure required to route transaction messages in realtime into an in-house analytics system. Deployments we managed through an inhouse deployment pipeline. We also provide the ongoing maintenance and support.


Technologies: Docker Swarm, Kafka, Zookeepr, Flink, Elasticsearch, Kibana, Puppet etc.

Customer Location: Switzerland

Big Data Analytics
IoT

Realtime Transaction Analytics Platform

A platform for financial transaction processing, customer segmentation and predictive analytics for banks to channel merchant offers to their customers. The solution has been deployed in Europe and in the Far East. ( http://redzebra-analytics.com ). We provided the CTO services, Product Engineering and the Professional Services Team.


Technologies: Cassandra, Java (Spring), MySQL, Hive, ElasticSearch

Customer Location: UK / Germany

Customer Profile: Start-Up. Products installed at leading European and Asian Banks.

ML Based Transaction Categorisation

For a major European Bank we developed a system to automatically classify transactions by Merchant Category. Our System proved to have an over 90% accuracy for categorising Merchants ( compared to <50% using a framework based on Google’s Merchant Database). The transaction classification system is a core component underlying multiple solutions in Customer Segmentation, Marketing and Loyalty Management.


Technologies: LevelDB, Python, NLP Libraries, SparkML

Customer Location: Europe

Customer Profile: Leading European Bank

predictive analytics
machine learning

Customer Segmentation and Analytics Dashboard

For a major Global Bank we developed a system segment customers based on their card transaction history. The system analysed 100s of Millions of Transactions to derive the basic segmentation Characteristics. The Dashboard was capable of presenting the segmentation of over 20 Million Customers in real time.


Technologies: Hive, ML and NLP Algorithms, ElasticSearch, Java (Spring)

Customer Location: AsiaPAC

Customer Profile: Leading Asian Bank