Kalyan Kumar Rachakonda
+91-958**-***** email@example.com Hyderabad, IN
Certified Data Scientist Professional skilled in Machine learning models, Data Analysis, Business Analysis, Natural Language Processing, Big data, Recommender Systems, Analytical and Statistical Skills
. Proficient in Python, R, SQL,Tableau. Adept in conducting data analysis, deriving insights and recommending relevant solutions.
• Data Analysis •Natural Language Processing • Computer vision • Model Deployment •BIG Data • Deep Learning
•Recommender Systems • Predictive Modeling • Data Mining • Data Visualization •AWS(Amazon web services) CERTIFICATIONS
KEY DATA SCIENCE PROJECTS
Language: Python, R, SQL
Visualization Tools: Tableau, ggplot, Matplotlib, Seaborn Platforms: Windows, Linux (Ubuntu)
Other Applications: Microsoft Office
Statistical and Machine Learning Skills: Linear Regression, Logistic Regression, Decision Tree, Random forest,Principal Component Analysis, Recommender Systems.
XGboost,SVM and KNN, Time Series analysis - Holt winters, MA, ARIMA. K-means clustering and hierarchical clustering.
k-Fold Cross-validation, Hyperparameter tuning.
Data visualization in R by deploying ggplot2 and plotly for interactive graphs. Data Visualization in Python by deploying Matplotlib, Seaborn, plotly and cufflinks. Feature engineering, Missing value and outlier handling, Transforming variable, creating new variables, Reshaping data using packages like dplyr and tidyr in R.
using packages like Pandas, Numpy and Scikit Learn in Python. ROC, AUC, KS, Accuracy and lift performance matrix. Big Data with Spark in Python.
Neural Nets and Deep learning (ANN,CNN) with TensorFlow and Keras in Python Knowledge on Computer vision techniques with OpenCV Certified Business Analytics Professional Edvancer Eduventures Feb '19 - Sep '19 Certificate of Excellence in Data Analysis Using SQL Edvancer Eduventures Aug '19 - Sep '19 Certified Tableau Professional Edvancer Eduventures Aug '19 - Sep '19 Certified Text Analytics Professional Edvancer Eduventures Sep '19 - Oct '19 Certified Data Analytics Expert Edvancer Eduventures Feb '19 - Oct '19 Python for Data Science and Machine Learning Bootcamp Udemy Oct '19 - Nov '19 Objective: A retail company wanted to open a new store over the next one year across multiple locations Tech Stack: Python (jupyter notebook)
Solution: Designed Random forest models to predict if a store should be opened or not in a particular location Key Achievement: Identified 25 locations for opening new stores, with the model achieving an accuracy of 85% II) Real Estate
III) Fake News Detection
IV) Credit Card Fraud Detection
VI) Human Resource
VII) Sentiment Analysis On Amazon Reviews:
Swarna Bharathi Institute of Science
and Technology, Jawaharlal Nehru
Master of Business Administration Sep '17 - Oct '19 ADDITIONAL INFORMATION
Objective: A real estate agency wanted to reduce the negotiation time and improve closure for buyers and sellers of homes by ensuring that both sides were advised well on the potential sale/purchase price of the home. Tech Stack: Python (jupyter notebook)
Solution: Created Random forest regression using Python to arrive at a potential transaction price for all future transactions
Key Achievement: Proposed a reduction in negotiation time from an average of 3 weeks to 8 days & a 25% jump in closure
Objective: Detected fake news by distinguishing fake and actual news. Tech Stack: Python (jupyter notebook)
Solution: Built TfidfVectorizer and initialized a PassiveAggressive Classifier to the model. Key Achievement: Detected fake news with accuracy of 93% Objective: Detected the credit card transaction fraud. Tech Stack: Python (jupyter lab)
Solution: Deployed Deep learning model mode with keras. keras Enhanced 3 hidden layers with Rectified linear unit and SSiiggmmooiidd activation functions
Key Achievement: Achieved a model accuracy of 99% and predicted the classes. Objective: A bank was rolling out a new term deposits product and wanted to predict which of their existing customers to target as part of maximizing ROI
Tech Stack: R
Solution: Deployed Logistic regression to create a propensity model to predict those customers most likely to respond positively to the new product and the campaign
Key Achievement: Achieved a model accuracy of 92% and registered a KS score of 64% Objective: A mid-sized IT company needed to plan its hiring and reduce risk of projects getting delayed due to employees leaving. It also wanted to understand why its attrition rate was high and how it could be reduced Tech Stack: R
Solution: Designed Decision tree model along with a Random forest model to predict attrition and also to better understand the factors related to attrition taking place Key Achievement: Achieved a model accuracy of 90% .Communicated the findings to the client Tech Stack: R
Sentiment Analysis Showed More Positive feedback, feedback which was left by people who bought products and got satisfactory out of them. Less people expressed Disgust Feeling, Feeling However some customers expressed Other sentiments as well. Languages: English, Telugu and Hindi
Secured 1st Prize among 100 entries in Think-Tank, Adsomniac and Business Quiz in vidwan Organized By S.B.I.T college Secured 2nd place among 50 competitors in Short Films Competition in Bomma premier league Organized by BOMMA college