Kiran Kondisetti

***, ******* **, *** **.***

+1-520-***-**** adegp1@r.postjobfree.com medium.com/@kirankondisetti34 kirankondisetti kiran-kondisetti Education

Texas A&M University (College Station), Masters in Industrial Engineering CGPA : 4/4 2019 - Present Texas, USA Focus: Statistical Machine Learning, Mathematical Optimization VNR VJIET, B.Tech Major in Mechanical Engineering CGPA : 8/10 2015 - 2019 Hyderabad, India Skills

Languages Python, R, SQL, C, GNU Octave, MATLAB

Frameworks/Tools Pandas, Numpy, SciPy, Scikit-Learn, TensorFlow, Pytorch,SymPy, Github, MS Office,Tableau Background Machine learning, Linear& Non-Linear Optimization, Computer Vision, Deep Learning, Inferential Statistics Software Packages R Studio, Jupyter Notebooks, Spyder, Visual Studios Projects

Detecting Attack by Malicious Executables using different Machine Learning models College Station, Texas

GITHUB JAN. 2020 - MAY. 2020

• Employed data processing techniques like validation, normalization and sorting of the given malicious software dataset

• Designed a decision tree using ID3 algorithm, used different pruning techniques to improve the accuracy of the model and checked the mean accuracy along with confidence interval using K-fold cross validation

• Built and trained a perceptron andmulti-layered perceptron using all the feature, tested themodelsusingK-fold validation and plotted an ROC curve to choose the best threshold

• Compared two ensemble learning models constructed using decision trees, perceptron, and MLP to select the most accuracte model which had an accuracy of 99.98%.

Data Analysis on Socio-Economic Factors Affecting Cancer Mortality College Station, Texas

GITHUB JAN. 2020 - MAY. 2020

• ExploratoryDataanalysiswas done to determine the distribution of the data, the most promising features, missing values, outliers etc.

• Developed Linear regression and SVM models for predicting the Cancer mortality, and to find the correlation between the predictors and the response variable

• Developed a KNN model for predicting cancer mortality and calculated the value of K that minimizes the test MSE by 0.5% and compared the model performance (MSE) of LR, SVM and KNN to find out which model had a better accuracy in predicting cancer mortality Generation of IMDB Recommendation Movie List Using SQL College Station, Texas

GITHUB SEP. 2019 - DEC. 2019

• Employed data preprocessing techniques on the IMDB movie dataset to know the trends in the data

• Applied SQL and used different operators to generate the best recommendation list based on the genre of themovieauserwatchedpreviously. Estimating the Quality of Red and White Wine using ML Models College Station, Texas

GITHUB MAR. 2020 - MAY. 2020

• Wine quality is predicted by using both classification and regression machine learning techniques like SVM, Random Forest, Boosting after cleansing the data

• Implemented a new metric (Z-score) to check the prediction percentage of each class present in the target variable of the model. COVID-19 Diagnosis using Neural Networks for Image Classification (Computer Vision) College Station, Texas

GITHUB APR. 2020 - Present

• Developing a fully automatic framework (CNN) for the diagnosis of respiratory infectious diseases, specifically a COVID19 infection, using Chest X-Ray Scan using the COVID-19 RADIOGRAPHY DATABASE in kaggle

• Implementing optimization techniques and hyper-parameter tuning to improve the classification accuracy. Predicting the Survival of Titanic Passengers College Station, Texas

GITHUB MAR. 2020 - MAY. 2020

• Preprocessing and Exploration of data is done to find the missing values, probability distribution etc.

• Different classification models like decision tree, LDA, QDA etc are used to predict the survival of each passenger.Hyper-parameter tuning of Random Forest is done to increase the accuracy 5%. Key Courses

Courses (Acedamic,

Coursera & LinkedIn)

Engineering Data Analysis, Machine Learning, Python for Data Science, R Statistics Essential Training, SQL for Data Science, Non-Linear Algebra and Dynamic Programming (NLP),CNN, Time Series Analysis JUNE 18, 2020 KIRAN KONDISETTI · RÉSUMÉ 1