CHANDRAKANTH NAIDU GONUGUNTLA

Motivated data scientist with 9 months of experience as a data science Intern at INNODATATICS. Passionate about building models that fix problems. Relevant skills include machine learning, Natural language processing, Deep learning, Data visualization, very good team player, strong communication skills. Motivated to learn, grow and excel my experience with challenging myself.

September 2021 - Current

DATA SCIENTIST

INNODATATICS

Bengaluru, Karnataka

• Assisted Data Scientists in collecting, analyzing, and interpreting the data sets for the improvement of product development.
• I helped in developing custom data models and necessary algorithms to apply to the data sets.
• Coordinated with different functional teams to implement models and monitor outcomes.

TITLE: AMAZON PRODUCT REVIEW
Duration: 6th April - 21st May

Project Type: NATURAL LANGUAGE PROCESSING

Business Objective

To get daily Analyses of a product such as emotions, and sentiment using Amazon data.

Roles and Responsibilities

• Extracted all the reviews of an amazon product and converted the data into a CSV file using python libraries and apps.
• Completed following Data-cleaning and text preprocessing steps using NLTK, spacy, sklearn(CountVectorizer, tfidf), re, BeautifulSoup libraries.
• Calculated the sentiment scores of reviews using Afinn, and Textblob libraries, and Based on their sentiment score Reviews are termed as Positive / Negative.
• Presented overall model interpretation, and insights to the client and deployed using Flask and Heroku.

TITLE: AIR QUALITY PREDICTION USING CO2 EMISSION LEVELS

Duration: 8th Feb -25th March

Project Type: FORECASTING MODEL

Business Objective

The objective of the project is to forecast Co2 emission levels for an organization.

Roles and Responsibilities

• Given Dataset contains only two columns Year and Co2 levels. It is Time series data, No ML models work here.
• Analyzed and understood the data, done EDA using python. Explained the trends and seasonality of data with teams, and led meetings and discussions.
• Various ARIMA models were built and performance has been evaluated by changing (p, d, q) values, model having less RMSE value is finalized.
• Presented overall model interpretation and deployed using Streamlit.

TITLE: CO2 EMISSIONS RELEASED BY SEVERAL CAR ENGINES FEATURES

Duration: 18th Nov 2021- 3rd Jan 2022

Project Type: REGRESSION MODEL

Business Objective

The fundamental goal of the project is to model the CO2 emissions as a function of several car engine features.

Roles and Responsibilities

• Analyzed and understood each of the technical details related to the business case, done EDA using python.
• Explained the data insights, outcomes, and experimental findings with teams, and lead meetings and discussions.
• The imbalanced dataset has been balanced with SMOTE technique and the columns with multicollinearity have been removed.
• Various Machine learning models were built and performance was evaluated by various evaluation metrics and Random forest has 98% accuracy.
• Presented overall model interpretation, and insights to the client and deployed using Flask and Heroku.

Languages(Data Science)
Python

Unsupervised ML
Clustering (K-Means, Hierarchical, DBScan), Association rules
Association Rules, RecommendationEngines
Data Visualization
Tableau
Database Management
MYSQL(workbench)
Python Libraries
Pandas, Numpy, Scikit learn, Matplotlib,Seaborn, NLTK
Supervised ML
Linear and Logistic Regression, SVM,Naive Bayes, KNN, Decision Tree,Ensemble Model
Convolutional Neural Network(CNNs)

NLP
NLTK, Spacy, Text Mining, BERT
Microsft Office
Excel, Powerpoint, Word

• DIPLOMA in DATA SCIENCE in ExcelR Institute, 2021
• TEXT ANALYTICS in IBM, 2021

I, CHANDRAKANTH NAIDU GONUGUNTLA, hereby declare that the information contained herein is true and correct to the best of my knowledge and belief.

___________________ Bengaluru, Karnataka