Tawab Shakeel

I'm

About

Data Scientist

I am an experienced Data Scientist working in the Financial Sector. Skilled in Machine Learning, Deep Learning, and Natural Language Processing,
Currently Researching on Explainable AI with the team of Researchers of Newyork University (NYU)

  • Phone: +92 3222200150
  • City: Lahore,Pakistan
  • Email: tawab2013@gmail.com
  • Freelance: Available

Skills

Python 100%
Pandas100%
Numpy 90%
Matplotlib/Seaborn 90%
PySpark 85%
Dask 85%
H2o Auto-ML 80%
Catboost 80%
Keras 80%
C++ / C 75%
MYSQL 95%
SNOWFLAKE 90%
Postgres 85%
Mongo Db 80%
Redis 75%
Machine Learning 90%
Natural Language Processing (NLP) 85%
Deep Learning 80%
Explainable AI (Researching) 70%

Resume

Sumary

Tawab Shakeel

Innovative and deadline-driven Data Scientist with 2 years of experience on different kind of Data Science Problems .

  • Lahore, Pakistan
  • +92 3222200150
  • tawab2013@gmail.com

Education

Bachelor of Science in Computer Science (BS CS)

2014 - 2018

Punjab University College of Information Technology

A-Levels

2012 - 2014

National Grammar School (NGS)

O-Levels

2010 - 2012

LaurelBank School System

Certifications

Machine Learning by Stanford University

Coursera

Applied Data Science with Python Specialization by University of Michigan

Coursera

Machine Learning and Reinforcement Learning in Python Specialization by NYU

Coursera

Data Scientist with Python (Track)

DataCamp

Machine Learning Fundamentals with Python (Track)

DataCamp

Professional Experience

Data Scientist at Project Work Groups (PWG)

2020 - Present

Remote

  • Worked on rural urban datasets of world bank
  • Identifying the problems in the marginalized communities

Data Scientist at Mltrons

2019 - Present

Remote

  • Developed Auto Cleaning Library to handle Data Wrangling using Pyspark
  • Developed Auto ML library using Python and Catboost Model (Currently More ML-Models are being integreated)
  • Responsible for handling Backend APIs for Mltron Dashbaord
  • Researching on Explainable-AI

Data Scientist at Big Byte Insights, Ltd

2018 - Present

Lahore, Pakistan

  • Developed Multiple Projects on Predictve Analysis on USA Real-Estate datasets
  • Responsible for handling Big Data Architecture for Data Science Project

Full Stack Developer at WebDealer Solutions

2016 - 2017

Lahore, Pakistan

  • Worked on development of Chatting Service
  • Responisble of handling Backend APis as well as Front End Design

Portfolio

  • All
  • Open Source
  • Clients Work
COVID VS WEATHER VS POLLUTION

Combined Covid cases with Pollution (pm2.5) and Weather (temperature) to figure out correlation Currently Used By Big Byte Insghts


ExplainX

ExplainX.ai is a fast, scalable & state-of-the-art explainable AI platform. ExplainX.ai helps data scientists understand, explain, debug and validate any machine learning model - in just one line of code.


DPTRON (Auto Cleaning Library)

Dptron is an in-memory platform built for distributed & scalable data cleaning & preparation. DPtron is written in Python and is built on PySpark to deal with large amounts of data seamlessly.


Multifamily Real-Estate Project For Big Byte Insights

Mulifamily is Home Type in USA.Predictive Analysis Using Statistical and Machine learning techiniques is done to Predict Comparison Metric i.e Year Over Year Change.Product of Big Byte Insights.

Auto Ml library

AutoMl library created using Catboost/Xgboost . Currently Used by Mltrons








Homebuilders Real-Estate Project For Big Byte Insights

Homebuilders is Home Type in USA.Predictive Analysis Using Statistical and Machine learning techiniques is done to Predict Comparison Metric i.e Year Over Year Change.Product of Big Byte Insights.



Different Neural Networks Implementations Using Keras

Implementing Different Neural Networks using Keras library. This Project is inspired by the blog of Andrew Tch





MLTRON Model Building Dashboard

It is a Virtual Data Scientist Platform that perform every task from Feature Engineering,Model Building to Model deployment. It is the major Product of Mltrons.



Document Similarity Using NLP

It is a Platform to find similarity between two documents using different NLP techniques such as Cosine Similarty etc



Data Camp Projects

These are the Data Science/Machine Learning projects available on DataCamp


Services

Predictve Analysis

Our Predictive Models uses best feature selection algorithm,use cross-validation technique to break through the noise in Big Data and deliver best outcomes /results

Customer Segmentations

Help Business to develop focused Strategies that can lead to higher customer growth

Machine Learning Development

Provides End to End solution from Machine Learning Model Building to Model Deployment

Deep Learning Development

Provides End to End solution from Deep Learning Model Building to Model Deployment

Text Analysis

Provide services to build products related to Natural Langauge Processing

Python Developement

Provide services of Automatic Workflow Scripts

DataBase Managements

Helps in integrating products with different Databases Systems i.e MySQL,POSTGRES,MONGODB,SNOWFLAKE etc

Contact

Location:

Lahore Pakistan

Call:

+92 322 220150