Post Job Free

Resume

Sign in

Data Scientist, Machine Learning Engineer, NLP Engineer.

Location:
Albany, NY
Salary:
65000
Posted:
January 30, 2021

Contact this candidate

Resume:

SUMMARY

Prajwal is a Graduate student pursuing MS in Data Science from University at Albany - State University of New York (SUNY) and will be graduated in May 2021. Experience in executing model development/building projects and extensive knowledge in Data Science, Machine Learning, Natural Language Processing (NLP) in Python

SKILLS

Prajwal Hegde

Data Scientist

518-***-****

adjtrd@r.postjobfree.com

Albany, New York

Core Competencies

Data Science

Machine Learning

Natural Language

Processing (NLP)

Predictive Modeling

Python

Data Visualization

Statistics

Problem Solving

SQL

Technical Skills and Experience

Data Science Techniques and Data Analysis:

Exploratory Data Analysis using Descriptive Statistics; Data Preprocessing Techniques; Univariate Analysis; Bivariate Analysis; Multivariate Analysis; Outliers Elimination; Feature Engineering techniques; Re-sampling method; Data Transformation techniques; Classification analysis; Regression analysis; Clustering analysis; Regularization.

Machine Learning Techniques of Supervised & Unsupervised algorithm and Statistical Analysis:

Logistic Regression; Decision Tree algorithm; Random Forest algorithm; Support Vector Machine (SVM); K-Nearest neighbor (KNN); Naive Bayes; Linear Regression; K means clustering; Principal component analysis (PCA); Ensemble Techniques.

Natural Language Processing techniques using Spacy and NLTK package in Python:

- Feature Reduction and Text preparation techniques using Noise removal, Text normalization like Lemmatization or Stemming, Spelling correction;

- Feature Extraction techniques using Count Vectorizer, TF IDF (Term frequency- inverse document frequency), Word Embedding by Word2Vec;

- Semantic Analysis by Semantic Extraction or Information extraction using Named Entity Recognition and Part of speech tagging;

- Text visualization using Word Cloud and Analyze Keyword Trend using uni- grams, bi-grams & tri-grams;

- Topic Modeling using Latent Dirichlet Allocation (LDA).

Model building: Binary Classification Model, Text Classification model, Clustering method, Predictive Modeling.

Programming Skills: Python with skilled in libraries such as Sklearn, Numpy, Pandas, Spacy, NLTK

Python Visualization Libraries: Seaborn and Matplotlib, Tableau.

Statistics

Analytical ability to derive insights from data.

SQL and MySQL.

Platforms: Anaconda, Jupyter Notebook, Spyder, MySQL Workbench.

Other skills include MS Office (MS Excel, MS Word, and PowerPoint.) EDUCATION

MS in Data Science, University at Albany, State University of New York (SUNY) - May 2021 (Expected)

Bachelor of Engineering in Electronics and Communication, VTU University, Bangalore, India – graduated in 2017

PROJECT EXPERIENCE

Have 3 Data Science

and Machine

Learning Project

Experience

• Built Random Forest Classifier model to predict class labels of the attrition level of an employee and recommend ways to decrease attrition level in the future.

• Developed Support Vector Classifier model to predict class labels of the smart meter and identify the reasons leading to non-communication from the smart meter to the electric supplier. Also, discover which smart meter company is producing non-communicating smart meter to reduce the business with the particular smart meter company.

• Built Logistic Regression model to predict class labels of employee’s performance ratings and recommend ways to improve the performance rating of the employee.

Have 4 Natural

Language Processing

(NLP) and Machine

Learning Project

Experience

• Developed Text classification model to classify work order gets exemption on penalty of SLA breach or not based on the historical data.

• Topic modeling using the LDA algorithm to identify reasons for SLA breach to get exemption on penalty and label the data based on the clustering of words in each topic.

• Word Cloud using Named Entity Recognition on the numerous eBay competitors to understand what competitors are focusing on based on the product, technology, geopolitical regions, and organizations.

• Data Scraping from Multi-Word Documents to CSV using Web Scraping technique.

CERTIFICATIONS

Completed and certified Zero to Hero Python Boot camp from Udemy. DECLARATION

I declare that all the above information provided is accurate to the best of my knowledge and belief.



Contact this candidate