Built robust regression and classification machine learning models by designing a test harness to evaluate a number of standard algorithms on the data and select the top few to investigate further.  Performed algorithm tuning and ensemble methods to get the most out of well-performing algorithms on your data.Data quality verification ensuring it via data cleaning. Training models and tuning their hyper
parameters. Used data transforms in order to better expose the structure of the prediction problem to
modeling algorithms

Excellent understanding with SciPy and NumPy , Matplotlib API, Pandas API and scikit-learn API

Gained hands-on experience in Alteryx analytics tool to build time series forecasting model (ETS) with
TS model factory and TS forecast factory Macros that forecasts energy consumption which help prevent
water and energy consumption.

POC completed by analyzing the client needs and document, design and build chatbot using IBM
Watson AI platform.
 Using GitHub to clone the Watson-Assistant repository (Node.js) to expand the business logic as per
business requirements.
 Configuring the app environment such as renaming environment variables and creating service wrapper
 Deploying modified version of app to IBM cloud with the cloud foundry command - line tool
 Installing the demo app package into the local Node.js runtime environment and testing the app
 Performed NLP techniques in building NLP chatbot. Sentence Classification using Machine Learning.
 Classifying text using ML algorithms such as NaiveBayes classifiers and scikit-learn Random Forest
model. Extracting sets of POS-tag Triples from a sentence

CNN based Image Classifier using TensorFlow and Keras in Colab Notebook

used 60,000 images to train the network and 10,000 images to evaluate how accurately the network learned to classify images. Accessing the Fashion MNIST directly from TensorFlow, using the Datasets API