Descriptive statistics, Probability
statistics, Linear and Logistic
regression, Regularization, Storytelling
Supervised Learning: Decision Trees,
Random Forest, Support Vector
Machines, K-Nearest Neighbours,
Naive Bayes Classifier, Time series
Unsupervised Learning: Clustering
Text mining concepts, Latent
Semantic Indexing and Search, Text
classification, Sentiment analysis.
AI and Decision Sciences
ANN, Deep learning, CNN and RNN
Processing frameworks like Map-
Reduce, Spark, SQL, Sqoop, Hive
Data Analyst professional seeking challenging opportunity to work for an organization. Hardworking,Optimistic and Condent with good interpersonal skills.
2019 APR -
Data Science Intern
Predictive & Descriptive analysis, Feature Engineering, Machine Learning modelling, Data Visualization
2014 - 2016 M.E IN COMMUNICATION SYSTEM
EASA COLLEGE OF ENGINEERING AND TECHNOLOGY
CGPA : 8.07
2010 - 2014 B.E IN ELECTRONICS AND COMMUNICATION
EXCEL ENGINEERING COLLEGE
CGPA : 7.42
PGP IN BIG DATA ANALYTICS AND OPTIMIZATION
Machine Learning A-Z : Hands-On Python & R in Data Science online course
Estimating Bias and Variance for different machine learning models The main objective of the project is to nd bias and variance for 5 different machine learning models and conclude which models are bias and variance sensitive. Estimated bias and variance on both regression and classication models.
Algorithms Used: Decision Tree, Random Forest, KNN, SVM(for both classication and regression), Linear Regression, Logistic Regression. Language Used: Python
Classication problem which had been described a tennis shot is a winner, an unforced error or a forced error
The given problem is Supervised learning and Multi class classication . Target variable 'outcome' is categorical with labels W/UE/FE. Algorithms Used: Decision Tree, Random Forest.
Highest accuracy got in Random Forest with 87%.
Languages Used: R
Predict The customer value for a retail store based on different quantitative and qualitative features
Data Science Projects
Predicting the "Customer Value" in a retail store as High/ Medium/ Low. Built different machine learning models to classify the customers as High/ Medium/ Low by using transactional and demographics data. Algorithms Used: Logistic Regression, Decision Tree, Random Forest, KNN, Naive Bayes.
Highest accuracy got in Random Forest with 68.3%
Languages Used: Python and R
Higgs Bosons particle detection
Classication problem which distinguishes a Signal Process which produces Higgs bosons and a background process which does not.
The features are kinematic properties measured by the particle detectors in the accelerator and the remaining features are high-level features derived by physicists to help discriminate between the two classes.
“Class” variable is target variable which is binary and has values 0&1 where 1 denotes a signal process which produces Higgs bosons and 0 denotes background process which does not. Removed some irrelevant features. Logistic Regression was applied because the target variable is a categorical
Two models was generated one with step AIC + standardization and got an accuracy of 64%. Second was without step AIC and got less accuracy in that. Languages Used: R
Text Classification in health care services
Based on the Text in the summary and description of the call written in "converse" column, the ticket is to be classified to appropriate category(out of 21 categories). Preprocessing: Removing stop words, Lemmatization, Label Encoding, Tokenizer Algorithms Used: CNN, ANN, LSTM
Languages Used: Python
Highest accuracy got in ANN.
INDIAN SOCIETY FOR TECHNICAL EDUCATION
Participated in Srinivasa Ramanujan Mathematical Competitions 2012 Achievements