Samar D.

Samar D.

Data Science Specialist - Machine Learning/NLP/Deep Learning

Chennai , India

Experience: 8 Years

Samar

Chennai , India

Data Science Specialist - Machine Learning/NLP/Deep Learning

54000 USD / Year

  • Start Date / Notice Period end date: 2019-09-04

8 Years

Now you can Instantly Chat with Samar!

About Me

Python

Programming

Pandas

NumPy

SQL

Scikit-learn

TensorFlow

PyTorch

Jupyter Notebook

Data Visualization

Data Manipulation

Data Cleaning...

Data Visualization

Data Manipulation

Data Cleaning

Probability/Statistics

Machine Learning

Deep Learning

Natural Language Processing

Show More

Portfolio Projects

Finding Donors project

Company

Finding Donors project

Description

  • Goal with this implementation was to construct a model that predicts whether an individual makes more than $50,000.
  • In a non-profit setting, where organizations survive on donations, this helps in determining how large of a donation to request.
  • Employed several supervised algorithms to model individuals' income using 1994 U.S. Census data.
  • Then chose the best candidate algorithm from preliminary results. Further optimized this algorithm to best model the data.

Show More Show Less

Tools

Github

IMAGE CLASSIFIER PROJECT

Company

IMAGE CLASSIFIER PROJECT

Description

  • Trained an image classifier to recognize different species of flowers.
  • This is somewhat similar to a phone app that tells you the name of the flower your camera is looking at. In practice you'd train this classifier, then export it for use in your application.

This was done using this dataset of 102 flower categories and transfer learning (a deep learning model trained on hundreds of thousands of images) as part of the overall application architecture

Show More Show Less

Tools

Github

DISASTER RESPONSE

Company

DISASTER RESPONSE

Description

o The primary challenge was to provide a way for disaster response organizations then becomes to filter out the relevant and most important messages from millions of messages they receive following a disaster.
o Used NLP techniques like Count Vectorizer, TF-IDF to process this data and then train a supervised machine learning algorithm to classify disaster messages to appropriate categories.
o Used various optimization techniques to achieve ~95?curacy in prediction
o Using this application, an emergency worker can input a new message and get classification results in several categories and then route the problems to appropriate organizations.

Show More Show Less

Loan Prediction

Company

Loan Prediction

Description

  • The goal for this project was to automate the loan eligibility process based on customer details provided during the online application.
  • Performed Feature Engineering and various machine learning techniques to identify key features and create additional predictive features.
  • Used Exploratory Data Analysis to draw important insights about the data.
  • By implementing the solution, most eligible customers can be identified so that businesses can specifically target those segments of customers.

Show More Show Less

Tools

Github

HR ANALYTICS

Company

HR ANALYTICS

Description

  • The objective was to analyse the employee’s attritions by looking at historical HR attritions dataset.
  • Used Exploratory Data Analysis to identify important insights about the data.
  • Performed Feature Engineering and different machine learning techniques to identify key features.
  • By implementing the solution, HR professionals can identify employee attrition and manage their organization’s manpower.

Show More Show Less

Tools

Github
Share:

Verifications

  • Profile Verified

  • Phone Verified

Preferred Language

  • English - Fluent

  • Bengali - Native/Bilingual

  • Hindi - Fluent

Available Timezones

  • Dubai [UTC +4]

  • New Delhi [UTC +5]

  • China (West) [UTC +6]

  • Singapore [UTC +7]

  • Hong Kong (East China) [UTC +8]