Saba Shah

About Saba Shah

10+ years of experience in statistics, machine learning, and solving problems using big data. Hands on with the Python data stack (pandas, sklearn, etc). Experience with deep learning using Tensorflow and Spark.• Leading offshore and onshore agile data science teams and serving as an architect for implementing industry best practices in AI application architecture for production pipelines and MLOps.• Experience in designing, building and maintaining big data and machine learning pipelines in production. Experience building client solutions for offline predictions on IoT, mobile phones and laptops.• Top 10% in Kaggle Homesite Quote Conversion Project.• Experience optimizing Machine Learning algorithms like Naive Bayes, Random Forests, Logistic Regression, SVM and Neural Networks. Experience in NLP including Twitter Text Classification. • Experience with Python\'s scikit learn, numpy, scipy, pandas and ggplot libraries. Well versed in R and Matlab. Hands on with Tableau and Qlikview. • Hands on experience implementing recommender systems with predictionIO and otherwise. Experienced handling cold start problems etc.• An active Kaggler with one published research paper \"Predicting Purchased Policy for Customers in Allstate Purchase Prediction Challenge on Kaggle\"(AICS2014) based on one of the competitions in Kaggle.• Familiar with architectural processes – Business Process reviews, Requirements capturing, Conceptual, Logical and Technical views and Design requirements• Extensive experience as a web developer/web application developer, focused on heavy design and development of different domain web based solutions. • Highly skilled with object-oriented programming and architectures, systems analysis, application development with effective and efficient coding practices. • Skilled at agile software development with ATDD. Experience working with github, Jira, Confluence.Programming Languages: Python, C#, HTML, XML, T-SQL and R

Experience

1. Senior Solutions Architect - Cloud - Data - Ai

   Databricks

   Aug 2023 — Present · US

Education

• Coursera

  Data Analysis by John Hopkins University, Data Analysis

  2011 — 2012

• Coursera

  Introduction to Data Science by University of Washington, Data Analysis - Data Science

  2013 — 2013

• Coursera

  Machine Learning by Stanford University, Machine Learning

  2013 — 2013

• University of the Punjab

  BS, Computer Science

  2000 — 2005

• Shaheed Zulfikar Ali Bhutto Institute of Science and Technology

  MS, Computer Science

  2007 — 2010

Skills

• Statistical Data Analysis
• Oracle
• Data Mining
• Project Planning
• Programming
• Statistics
• Business Intelligence
• Badminton
• C++
• Business Analysis
• C#
• .net
• Oop
• Statistical Tools
• Mongodb
• Microsoft Sql Server
• Xml
• Ms Project
• Hadoop
• Databases
• Visual Studio
• Team Management
• Html
• Java
• Analysis
• Data Science
• Data Analysis
• Software Project Management
• Javascript
• Software Development
• Python
• Web Applications
• Semantic Web
• Cricket
• Scikit, Numpy, Scipy, Matplotlib
• Leadership
• Requirements Gathering
• Mysql
• Sql
• Asp.net