Piyush Kapoor

Product Manager

Gurgaon, Haryana, India14 yrs 10 mos experience

Highly StableAI Enabled

Key Highlights

Expert in Machine Learning and Data Analytics.
Proven track record in predictive modeling and customer segmentation.
Strong background in applied research and advanced data techniques.

Stackforce AI infers this person is a Data Science expert with a focus on Machine Learning and Business Analytics.

Contact

piyushkapoor7@gmail.com LinkedIn

Skills

Core Skills

Machine LearningData ScienceBusiness AnalyticsData AnalyticsApplied Research

Other Skills

AWS SageMakerAlgorithmsAmazon Web Services (AWS)AnalyticsAnalytics ManagementApache NifiArtificial IntelligenceArtificial Neural NetworksBig DataBig Data AnalyticsCC++Customer Relationship Management (CRM)Customer SegmentationCustomer Segmentation Strategy

About

Experienced Data Analyst / Scientist with a demonstrated history of working in the information technology and services industry. Skilled in Computer Science, Machine Learning, Artificial Intelligence, Business Intelligence, Advanced Data Analytics, Hadoop, Spark, Python, NLP, R, Informatica, Tableau, Matlab. Strong information technology professional with a M. Tech focused in Robotics from IIIT Allahabad.

Experience

14 yrs 10 mos

Total Experience

3 yrs

Average Tenure

2 yrs 10 mos

Current Experience

Adidas

Manager - Data Science

Aug 2023 – Present · 2 yrs 10 mos · Gurugram, Haryana, India

Using Machine Learning (in particular tree-based models, NLP, image processing), exploratory data analysis and feature engineering.
Statistics/ statistical inference  linear algebra, optimization and time-series modelling.
Python and its state-of-the-art analytical libraries (e.g., pandas, scikit-learn, PySpark, plotly). Deep Learning architectures (e.g., CNNs or RNNs) and experiment with tools like TensorFlow or PyTorch. Basic knowledge of R (including tidyverse)
Work in a Jupyterlab/ Notebook environment and with IDEs like PyCharm or Visual Studio Code or Spyder. Using Bitbucket/ GIT for version control and collaborative coding. Working with Databricks/ Sagemaker.
Relational databases and efficiently query large databases (e.g., via Spark, SQL, Hue).
Software engineering principles (e.g., integration/ unit testing) and the concept of continuous integration. Use of Jenkins.
Working in one of our focus areas (i.e., recommender and ranking systems, website personalization, search engine optimization, product ranging, sizing, tactical pricing, demand forecasting, image processing, social media listening, customer lifetime value).
Agile development
Applying data analysis, design, and modelling techniques to establish, modify or maintain a data structure and its associated components (entity descriptions, relationship descriptions,
attribute definitions).
Programming/software development
Designs, codes, verifies, tests, documents, amends and refactors moderately complex
programs/scripts.
Applying agreed standards and tools, to achieve a well-engineered result.

Machine LearningNLPImage ProcessingPythonData AnalysisStatistics+5

Samsung sds

Lead AI Consultant

Apr 2020 – Aug 2023 · 3 yrs 4 mos · Gurugram, Haryana, India

BA(Business Analytics) Consulting
Benchmarking project case based on global advanced case experience
Securing a model for industry-specific analysis and New Biz. Discover business opportunities
Analytics management solution consulting and building
Establish a predictive model, consult customer segmentation or use the PoC to validate your Analytics business
Inventory : Big data analytics business for Samsung affiliates
Future development trend and forecast: This technology area is a business that is essential for customers who want to introduce Business Analytics or implement Insight management system.
Customer Analysis Business Team Establish strategy for BA business and create visible results of BA and Big Data business through role of Data Scientist.
In the mid- and long-term, the competence of candidates can be acquired by other personnel.
Through the execution of big data business centered on various Samsung affiliates, it can grow into a specialized data scientist for each industry

Business AnalyticsPredictive ModelingCustomer SegmentationBig Data AnalyticsAnalytics ManagementData Analysis+1

Ncr corporation

2 roles

Senior Data Analytics – Analyst

Promoted

Nov 2018 – Apr 2020 · 1 yr 5 mos · Gurgaon, India

o Using SAFe Agile Framework throughout the life cycle of projects.
o Working in Supply Chain & HR Analytics Center of Excellence. Building data lake including data repositories pipeline which would enable next generation data analytics capabilities for business users. This involves building Data Ingestion, staging layer, transient layer, RDW Layer, hub layer & pub layer.
o Leading supply chain repository which involved data modelling, data discovery, repository code development, production deployment, data validation & process automation.
o Hive Queries Development for Staging, Transient, Hub & Pub Layer.
o Writing Python Code for automating Day to Day Manual Work for the team.
o Hive queries development for Merge Logic in Hub Layer
o Apache Nifi Development for Ingesting Data in to Hadoop / Data Lake across various ingestion channels.
o Sqoop Development for Structured / Semi structured and un structured data in to Hadoop / Data Lake.
o Machine Learning Based solutions including predictive modeling, Statistical Analysis & Advanced Data Analytics techniques to support business processes.
o Built Report Rationalization Model (Clustering) by using Hierarchical Clustering Model.
o Built a NLP Based Machine Learning model to predict the Remote resolution index for Walmart Remedy.
o Writing Python and Pyspark Automation Code for the team to manage routine Day to day work.
o Part of a team working in automating the end to end process of Data lifecycle across the layered architecture.
o Position is responsible for NCR Remote Services Management (RSM) data analytics within the NCR IT organization. The RSM program includes NCR Predictive Services, a managed service that analyzes diagnostic data from NCR serviced machines and predicts failures in advance of service interruption.

SAFe Agile FrameworkData LakeData IngestionPythonHive QueriesMachine Learning+3

Data Analytics - Analyst

Apr 2015 – Oct 2018 · 3 yrs 6 mos · Gurgaon, India

o Machine Learning Based solutions including predictive modeling, Statistical Analysis & Advanced Data Analytics techniques to support business processes.
o Built Report Rationalization Model (Clustering) by using Hierarchical Clustering Model.
o Built a NLP Based Machine Learning model to predict the Remote resolution index for Walmart Remedy.
o Writing Python and Pyspark Automation Code for the team to manage routine Day to day work.
o Assisting team in Managing Jira Boards, Sprint Planning, Sprint Retrospective Sessions, and Daily Stand Ups etc.
o Part of a team working in automating the end to end process of Data lifecycle across the layered architecture.
o Playing key role in mitigating the Machine Learning Based solution from classical platform to Big Data platform.
o Position is responsible for NCR Remote Services Management (RSM) data analytics within the NCR IT organization. The RSM program includes NCR Predictive Services, a managed service that analyzes diagnostic data from NCR serviced machines and predicts failures in advance of service interruption.
o Data Ingestion including both seeding and feeding of data. Data from multiple ingest channels like Informatica CDC, Real Time Data from Web services (SOA/SOUP, JMS etc.), Apache Nifi, FTS / CTS ( File transfer System), ETL (tools like Informatica Power Center) etc.
o Assisting in design, development, testing, deployment, and support of RSM data analytics systems. This includes machine learning and analytical model development.
o Built Tableau dashboards to demonstrate Leakage Analysis for Remote Resolution for clients across US including Walmart.
o Data Modelling of Supply chain Repositories ( Inventory, Purchase Order, Bill of Materials, Accounts Payable & Work in Process ) to built HUB Layer with Star Schema Architecture.
o Worked on building Raw  Hub  Pub Layered Big Data Enabled Architecture on Survey Data for HR Analytics.

Machine LearningPredictive ModelingPythonData IngestionData AnalyticsTableau

Kvantum inc.

Scientist - Applied Research

Jul 2013 – Apr 2015 · 1 yr 9 mos · Gurgaon, India

Projects / Research Tasks:
o Incremental PCA in C++: Implemented Co-variance free Incremental PCA on C / C ++ using Armadillo linear algebra library to improve the space and time complexity of RPCA with extensive use of pointers.
o Cubature Kalman Filter Parameter Optimization using PYMC:- Used PYMC python library, to find the initialization parameters of Cubature Kalman Filter.
o Multi – Level Modelling in python using PYMC:- Implemented basic structure of multi – level modelling in python by using PYMC library to find optimal solution through MCMC simulation.
o Recursive PCA in python: - Implemented Recursive Principal Component Analysis in python for streaming data so as to reduce its dimensionality.
o Recursive PCA on Hadoop: - Implemented Recursive Principal Component Analysis in Hadoop for distributed Computation so as to handle huge data of a client. Also the code handles variable dimensionality in the streaming data.
o Multi-Layer Perceptron Artificial Neural Network in python: - Implemented dynamic multi – layer perceptron model of Artificial Neural Network in python that uses Backpropogation as its learning algorithm.
o Bayesian Regression in Python: - Implemented Bayesian Regression python using PYMC library.
o Stacked Auto Encoder in python: - Implemented dynamic stacked auto encoder model of Artificial Neural Network in python.
o Kalman Filter using Markov Chain Monte Carlo Simulation in python: Pymc python library to use MCMC simulation in Kalman Filter.
o Extended Kalman Filter for training neural network in python: - Implemented extended Kalman Filter for the purpose of weight adjustment of Neural Networks in python.
o Written SQL Queries for CXO Links Project.
o Written a python script for data uploading to database from excel file containing raw data in Sodexo Links Project.
Awarded with Kvantum Core Value Award For Excellent Work in Research on 20-12-2013.
Awarded with Kvantum Core Value Award For Collaboration on 14-07-2014.