Based on details provided by customer, we have topredict that customer is eligible for loan or not.

I was involved in functional analysis of dataset and understanding of data.

Involved in Feature engineering and feature importance based on which feature selection was done.

Involved in choosing best AUC score for model and parameter tuning

Involved in saving model and contineous training.

Tech Used: Python, skLearn, matplotlib, seaborn, gc

By collecting data for one year of purchase made by customers, I had to anticipate the purchases that will be made by a new customer, during the following year and current one, from its first purchase.

I was involved in functional analysis of dataset and understanding of data.

Involved in Feature engineering and feature importance based on which feature selection was done.

Involved in choosing best AUC score for model and parameter tuning

Involved in saving model and contineous training.

Tech Used: Python, skLearn, matplotlib, seaborn, gc

Based on the provided information, I have to predict those customers who are likely to churn out of the bank in coming year.

I was involved in functional analysis of dataset and understanding of data.

Involved in Feature engineering and feature importance based on which feature selection was done.

Involved in choosing best AUC score for model and parameter tuning

Involved in saving model and contineous training.

Tech Used: Python, ScikitLearn

Based on the provided information i had to predict those employees tending to churn the company in coming year.

Involved in Feature engineering and feature importance based on which feature selection was done.

Involved in choosing best AUC score for model and parameter tuning

Involved in saving model and contineous training.

Analyzed communication between sales representatives and customers to predict whether a protection agreement was sold to the customer or not during the sale.

I was involved in word embedding and text cleaning

Involved in Parameter tuning and pipeline

Model deployment

Tech Used: Python, matplotlib, seaborn, nltk, ScikitLearn

Classify the comments retrieved from website as positive, negative and normal.

I was involved in text cleaning

Involved in Parameter tuning and pipeline

Model deployment

Tech Used: Python, matplotlib, seaborn, nltk, SkLearn

Opinion mining from twitter, analyzed given number of tweets for the product released by company provided by customer.

Tech Used: Sklearn, NLTK, Python, tweepy, TextBlob, wordCloud, seabron, matplotlib, gensim, keras

Opinion mining from twitter, analyzed given number of tweets for the product released by company provided by customer.

This web-based project is having worldwide scope, which caters the need the needs of company as a single and unique platform to define and management project including resources throughout the world.

It is a web Solution (CRMnext), fulfilling all the services required for the customer relationship management. The product enables to drive revenue, based on more effective management of their business processes.

There are provided cutoff for the execution of each query and each and every time it should execute. Need to continuously optimize query and stored procedure.