M. ShanmugaBharathy

Innovative Artificial Intelligence learner possessing strong mathematical skills and detailed knowledge of machine learning evaluation metrics and best practices. Expertise in predictive analysis, data mining and computational statistics. Logical and detailed professional with exceptional Python coding, SQL, C and C++

 NumPy, Matplotlib, Pandas, Scikit- learn, TensorFlow, Keras.

Linear regression, Logistic regression, Decision tree algorithm, Naïve bayes algorithm, KNN algorithm, K-means, Random Forest algorithm.

This project uses Plotting distribution, Visualization and Hypothesis Testing

· Answering Industry Problems through Statistical inferences

· Analyse past tournament information to make informative investment decisions.

· Analysing the status of various startups that participated in the Startup Battlefield

Supervised Learning

To predict the outcomes after an extensive EDA and work missing values, and imbalance in data.

· Predicting the condition of the patient depending on the received test results on biomechanics features of the patients according to their current conditions.

· Build an AIML model to perform focused marketing by predicting the potential customers who will convert using the historical database.

To build and train a prediction model for a telecom company powered by supervised learning and ensemble modelling techniques

· To identify the potential customers who have a higher probability to churn.

· To understand and pinpoints the patterns of customer churn and increase the focus on customer retention strategies.

· To build and train a prediction model to identify Pass/Fail yield of a particular process entity for a semiconductor manufacturing company.

· To determine key factors contributing to yield excursions downstream in the process and will enable an increase in process throughput, decreased time to learn and reduce per-unit production costs.

· This project is based on the order management functionality of an online retail store.

· To making data-driven decisions that will impact the overall growth of the online retail store.

· Classified vehicles into different types based on silhouettes which may be viewed from many angles.

· Used PCA in order to reduce dimensionality and SVM for classification.

· The objective of the project is to learn how to implement a simple image classification pipeline based on the k-Nearest Neighbour and a deep neural network.