Summary
Overview
Work History
Education
Skills
Timeline
Generic

Jawed Pasha Shaik

Johnston,RI

Summary

Experienced Data Scientist and Machine Learning Engineer with over a decade of proven success leveraging extensive datasets to derive actionable insights and solve complex business challenges. Expertise in data collection, preprocessing, feature engineering, and data augmentation, utilizing tools like Python, spark, and cloud-based solutions like AWS Sagemaker. Proficient in architecting and deploying end-to-end machine learning solutions, adept at the entire machine learning lifecycle from project scoping to performance monitoring. Skilled in designing and conducting experiments to optimize model performance and enhance decision-making. Known for driving informed decision-making through innovative analytical and engineering solutions tailored to diverse business needs.

Overview

11
11
years of professional experience

Work History

Machine Learning Engineer

Citigens Financial Group
03.2023 - Current
  • Worked closely with Product Owners and Application Managers to identify business problems that can be solved through Machine Learning
  • Worked closely with Project stakeholders to establish Project scope and Performance Baseline
  • Improved Data quality through Feature Engineering, Data Preprocessing, Data Wrangling and Data Augmentation on both Structured Data and Unstructured data
  • Designed and implemented binary classification solution for product attrition management prediction in commercial banking domain, focusing on proactive retention strategies.
  • Conducted comprehensive evaluation of classification algorithms including Random Forest, Decision Tree, and XGBoost. Selected XGBoost for its robustness in handling complex datasets and ability to capture nonlinear relationships.
  • Utilized grid search and cross-validation to fine-tune XGBoost hyper parameters, optimizing for metrics such as ROC-AUC, F1 Score and precision-recall curves. Achieved 15% increase in ROC-AUC over baseline models.
  • Conducted thorough EDA to understand data, designed preprocessing pipelines , engineered features and implemented monitoring systems to detect and mitigate data drift.

Data Scientist

Uber R & D
04.2021 - 11.2022
  • Designed and implemented mechanism to track cash flow within Uber disbursement systems and bank statements to identify outstanding payables which increased accuracy from 30% to 99.1%
  • Worked on implementing solution to capture Open account receivable balances periodically by identifying events across trips life cycle (trip occurrence, collections from customers and settlements from PSPs) ensuring completeness and accuracy with respect to Uber accounting books and reduced risk exposure to Uber P/L from 100M USD (MoM) to 90K USD.
  • Responsible for building pipelines for cleaning data, performing exploratory data analysis, and detecting outliers using Python for building predictive models.

Data Analyst

Uber R & D
03.2019 - 03.2021
  • · Developed framework and automated manual ledger preparation process for Uber Accounting team which allows accounts to prepare and download ledgers with one click of button.
  • Materiality of these ledgers would be around 30M USD and this initiative resulted more than 90% reduction in manual efforts on monthly basis.
  • Analyzing financial and accounting related information across entities with in client's organization (Uber R & D) to track all intercompany transactions and prepared tableau dashboard to draw insights and automate validations.
  • Worked on different requests from accounting, engineering and product teams across Uber helped them for smooth month close process.

Data Engineer

Capgemini
03.2018 - 03.2019
  • As part of Anti money laundering team for leading bank (HSBC), worked on designing and implementing detailed workflow to process all alerts triggered from rule-based transaction monitoring system.
  • Prepared multiple parts of workflow to collect alerts triggered, roll them up at different dimensions like account, customer, counter party and gather details from multiple systems, aggregate information and push data to downstream oracle systems to investigate further.
  • With help of Control M, scheduled and Automated entire workflow to collect alerts, roll them up, gather related information and push data into downstream Oracle system.
  • Migrated Orchestration services from Control M to AWS workflow orchestration.

Data Specialist

Tata Consultancy Services
01.2014 - 02.2018
  • Prepared mechanism to analyze forecast information for telecom equipment (for Ericsson) for future 24 months and break forecast at multiple dimensions and securing agreements and contracts to procure raw material.
  • · With help of spark and hive, implemented data pipeline to create single source of authorized data for all financial and regulatory needs of leading bank (BofA).
  • · Worked on migrating data from RDBMS data sources (Netezza, Oracle etc.) to data lakes in Hadoop platform by creating spark applications.
  • · Implemented Oracle Packages and SQL stored procedures to breakdown high level forecast information into least possible components to secure raw material.
  • Responsible for building promotional model based on frequent flyer information on customer credit cards.

Education

Bachelor of Technology - Electrical And Electronics Engineering

Acharya Nagarjuna University
Guntur, Andhra Pradesh
05.2013

Skills

  • Machine Learning and Statistical learning techniques
  • XG Boost, Decision Making, Random Forest, Regressions
  • Predictive Modeling, Clustering Techniques, A/B Experimentation, Hypothesis Testing
  • AWS Sagemaker, ECR, Auto ML, H2O,AWS S3
  • Pyspark
  • Python, Spark, Pyspark,Hadoop
  • Hive, Presto, Impala, SQL
  • Piper (Apache Airflow), Control M, Autosys
  • Tableau, Seaborn, Matplotlib
  • AWS Redshift, Athena, Glue, Snowflake, Cloud Data Warehousing

Timeline

Machine Learning Engineer

Citigens Financial Group
03.2023 - Current

Data Scientist

Uber R & D
04.2021 - 11.2022

Data Analyst

Uber R & D
03.2019 - 03.2021

Data Engineer

Capgemini
03.2018 - 03.2019

Data Specialist

Tata Consultancy Services
01.2014 - 02.2018

Bachelor of Technology - Electrical And Electronics Engineering

Acharya Nagarjuna University
Jawed Pasha Shaik