IoT Analytics:To analyze the sensor data captured from 1000+ heavy vehicles located at various construction sites across India. Using this data, define some Key Performance Indicators (KPI’s) to analyse the performance of vehicles so that they can take some measures to improve those and hence, their productivity and business. Descriptive & later on predictive modelling has to be built on KPIs of the vehicles.Text Mining:Misclassification Identification using text in product catalogues of E Commerce industry: Worked on US NO 1 retailer data to identify products which are not classified correctly. Also work focussed on identifying key attributes in the whole text and recommending correct shelf. Used traditional approaches TFIDF, Count Vectorizer models as well as modern approaches like word embeddings, word2vec, and Deep learning LSTM model. Experimented with wide variety of ML algorithms including Random forests, Isolation forest, single class SVMAutomatic Classification of Clinical Text Tickets (Text Mining): The provider follows a ticketing system for all the telephonic calls received across all the departments. Calls to the provider can be for New Appointment, Cancellation, Lab Queries, Medical Refills, Insurance Related, and General Doctor Advise etc. The challenge is, based on the Text in the Summary and Description of the call, the ticket is to be classified to Appropriate Category (out of 5 Categories) and Subcategories (Out of 20 Sub Categories).

E commerce Analytics: The biggest e-commerce center in Canada, providing a unique Canadian experience that combines an authoritative selection of products, unparalleled service and a social loyalty program that rewards members on every purchase. They wanted to analyze their logs which is getting generated from their website. We have involved from storing the logs in HDFS and analyze based on their requirement like the pages always gives an error code and which customer is accessing more pages etc.Insurance:The Azure Insurance Group consists of 10 property and casualty insurance, life insurance and insurance brokerage companies. The property and casualty companies in the group operate in a 17-state region. Mutual group is a major regional property and casualty insurer, represented by more than 4,000 independent agents who live and work in local communities through a six-state region. We need to define the metrics to analyze agent performance based on several attributes like demography, products sold, new business, etc. Azure is interested in improving their existing knowledge used for agent segmentation in a supervised predictive framework.