DATA SCIENTIST
ASLAM
[email protected] Mobile: +91 9182 671 382
PROFESSIONAL SUMMARY
Total 11+ years of IT Work Experience.
4+ Years Work Experience in Data Science with Machine Learning, Pattern
recognition with Data mining, Natural Language Processing (NLP), Deep
Learning, Predictive Modeling, Statistics, recommendation systems, Python
Flask and optimization algorithms.
6 years’ Work Experience in SAP ABAP as technical consultant.
Experience using Tensorflow,Keras,OpenCV,numpy,pandas,matplotlib,scikitlearn
Experience in Computer vision,Text analytics using nltk,Image analytics
Experience in Statistical Modeling / Machine Learning methods with hands on
experience handling data driven decisions
Proficiency in statistical and other tools/languages - Python, R
Ability to work on structured, semi-Structured and un-structured data.
Proven background in at least one of the following - Reliability models, Markov
Models, Stochastic models, Bayesian Modeling, Classification Models, Cluster
Analysis, Neural Network, Time Series analysis, NLP Models, Multivariate
Statistics
Processing, cleansing, and verifying the integrity of data used for analysis.
Working with data visualization tools Tableau to create real time visuals that give
proactive steps to support the business
Working experience as Techno-functional Business Solution Consultant
Liaising with global stakeholders from initiation to completion of projects.
Experience in working with databases and SQL in a business environment
Deep understanding of functional business processes and business modules.
Experience in working in diversified complex Business landscapes.
Ability to ponder solutions to eliminate the Root Causes.
Strong experience in Python and R and ABAP programming
Image processing and Image classification experience.
Python libraries-Sklearn,OpenCV,Pandas,NumPy,Matplotlib,CNTK,NLTK
Experience in various statistical and machine learning models, data mining,
unstructured data analytics in corporate or academic research environments
Develop forecasting models for key business services and answers to key
questions
Understand the business and industry and expand the reach of warehousing by
identifying and integrating internal and external sources of information
Experience leading or collaborating with a team of data scientists in developing
and delivering machine learning models that work in a production setting.
Use of development methodologies like SOA- Service Oriented Architecture,
FRICEW (Forms, Reports, Interfaces, Conversions, Enhancements and
Business Workflows).
WORK EXPERIENCE
Senior Consultant
Binary Fountain pvt ltd - Sep 2017 to till date
Tech Specialist
Tech Mahindra Limited - May 2011 to 2017
Sr Software Engineer
Siemens Info systems Pvt Ltd – Feb 2010 to May 2011
EDUCATION
Btech in Computer Science Engg - JNT University
ADDITIONAL INFORMATION
Technical Skill Set
Technical: SAP ABAP, SAP ISU
ERP: SAP ECC.
Programming: ABAP, R and Python.
Data Base: Queries using open SQL, Basics of DBMS.
Office Tools: Microsoft Office Suite- Word, Excel, PowerPoint, Access, Outlook.
Trainings Attended
1. Data Scientist Transformation Training at Mahindra Satyam (Tech Mahindra),
Bangalore.
2. Conference on Future Data Scientists and Big Data at Mahindra Satyam Tech
Mahindra, Hyderabad.
Projects
7. Project Name: NLP
Client Binary fountain
Role Team Member
Organization Binary Fountain
Duration 10/2017 – till date
Roles and Responsibilities
Implementation of KAFKA cluster with various application data being consumed
at Consumer groups and the result from NLP will be return to returntopics
NLP code analysis and removal of unwanted and unused variables and
comments within the existing python scripts.
Designed and implemented tone analysis using NLP.
Designed & implemented Category classification among several categories
present
Designed and implemented extraction of feature and opinion pairs within the
existing corpus of reviews
Designed and implemented a Machine learning model to predict patient Length
of Stay during the hospital.
Designed and implemented a model to predict the payment amount for a
procedure done
Designed and implemented a machine learning model for predicting the
Customers Churning analysis.
Developed a python script that will take two input csv files one is NLP output and
Manual output and calculate the number of accuracy and coverage that NLP
being done correctly and number of misses NLP made .
6. Project Name: Thomson Reuters
Client TCIPL
Role Team Member
Organization Tech Mahindra, India
Duration 05/2016 – 08/2017
Roles and Responsibilities
Manage the data quality audits/rules and generate the reports
Convert business rules into technical rules for data quality analysis.
Data analysis, creating work plans, programming in R, creating presentations for
the client, designing algorithms,
Designed and Implemented HR Employee attrition predicted using the Machine
learning Algorithm in R statistical tool.
Designed and implemented Sentiment analysis using NLP.
Designed & implemented demand generation incentive compensation plans for
leading brands to enable sales force representative to meet targets
Forecast the enrolling customers for the promotion activity introduced by client
using the Time series analysis using ARIMA model
Processing the images using Opencv and classification into right classes
Designed and implemented the image recognition and archiving using Deep
Learning Convolutional Neural Network.
Created territory alignment by considering area sales potential, sales force size
and geographical constraints.
Worked on creating and manipulating dashboards in Tableau as per the need.
Analyzed the trend, call planning schedule and eligibility constraints to derive
performance to target pay curves for representatives.
5. Project Name: Ahlstrom, Finland
Client Ahlstrom, Finland
Role Team Member
Organization Tech Mahindra
Duration 11/2015 – 03/2016
Project Description
Ahlstrom is a high performance fiber-based materials company, partnering with leading
businesses around the world to help them stay ahead. We aim to grow with a product
offering for clean and healthy environment. Our materials are used in everyday
applications such as filters, medical fabrics, life science and diagnostics, wallcoverings
and food packaging.
Developed custom Applications using Python Flask as per the client
requirements.
Develop and implement data collection systems and other strategies that
optimize statistical efficiency and data quality.
Acquire data from primary or secondary data sources and maintain
databases/data systems and deployed different predictive models using python
Scikit-Learn python framework.
Identify, analyze, and interpret trends or patterns in complex data sets in the
complete Supply chain Management areas of the client.
Work closely with management to prioritize business and information needs and
Locate and define new process improvement opportunities.
Develop & implement and manage data strategies that optimize the data quality
to improve standardization
Analyze and interpret the tweets from external sources and derive the conclusion
of the customers and other stakeholders using Python.
Created dynamic linear models to perform trend analysis on customer
transactional data in Python.
Identify the patterns& frequency of data in the dataset and prepare the reports.
Developed prediction algorithm using Random Forrest & logistic regression
techniques using Python statistical tool.
4. Project Name : ESGAP Project
Client GE
Role Team Member
Organization Tech Mahindra, India
Duration 01/2012 – 10/2015
Team Size Project : 8 Module : 4
Environment Software Languages : ABAP
(with skill versions) Database : Oracle
Tools : HPQC 10.0
O/s : Windows XP
Project Description
GE is an advanced technology, services and finance company taking on the world’s
toughest challenges. Dedicated to innovation in energy, health, transportation and
infrastructure.Headquartered in Atlanta, Georgia, U.S., GE Energy is one of the world’s
leading suppliers of power generation and energy delivery technologies. 82,000 global
employees serve the energy sector by developing and deploying technology that makes
efficient use of natural resources. Comprised of GE Oil & Gas, GE Power & Water, and
GE Energy Services, GE Energy's business units work together to provide integrated
products, services, and solutions in all areas of the energy industry, including coal, oil,
natural gas, and nuclear energy; renewable resources such as wind, solar, and biogas;
and other alternative fuels.
Contribution:
Closely worked with client to understand the requirements and contribute to
optimize the design.
Involved in Daily calls with the client to understand the daily progress.
GECARS interface developed from scratch to post the payments in SAP that
are received from Customers.
Z report to display the VAT details like Input ,Output Vat received.
Developed an overtime report for part time employees.
Debugged the programs to identify the problem(s) as requested by the
functional team.
Developed a payroll report for India which retrieves the payroll data from
payroll clusters.
3. Project Name : Thomson Reuters
Client TCIPL Bangalore Engagement
Role Team Member
Organization Tech Mahindra, India
Duration 06/2011 – 12/2011
Team Size Project : 85 Module : 25
Environment Software Languages : ABAP
(with skill versions) Database : Oracle
Tools : HPQC 10.0
O/s : Windows XP
Project Description:
This is a transformation and support project. The Billing to Cash Collection
program (B2CC) supports the integration of legacy Reuters and Thomson
Financial billing and receivables processes, by replacing the legacy systems
with one instance of SAP. The objective of the program is to develop one
global business process in the areas of billing and cash
management/collections, to improve customer experience, as well as to
rationalize and to modernize technologies globally by 2012.
Contribution
Wave 4 functionality added to create the international version of customers
and to change contract data to add legacy data and update values in custom
table created as part of another custom development.
Custom development for report that goes from SAP to external system
( FORE System) that in turn gets data from the other system the output
report will speaks the Control file as well as summary file that gives the
total number of local currency amount as well as the amount under each
currency this report is AR Open items for Reconciliation purpose.
Defects under the custom developments and interfaces.
Changes to an interface that fetches data from SAP to an External system
( Get Paid system ) which includes the output of 3 files like ARCUST:
Customer information that has matching in other files. Contains one record
per customer with open transactions. ARMAST: All open invoices. Contains
one record per open transaction (invoice, credit memo, open credit or debit,
balance forward, etc). Control File: This file contains the count of lines per file
provided. Inbound idoc for the External Customer Contacts for processing into sap system from
the source SIEBEL system.
2. Project Name : Xerox
Client Xerox
Role Team Member
Organization SISPL, India
Duration 08/2010 – 05/2011
Team Size Project : 50 Module : 20
Environment Software Languages : ABAP
(with skill versions) Database : Oracle
Tools : HPQC 10.0
O/s : Windows XP
Project Description:
Xerox is an American global corporation that sells business services and document
technology products to businesses and governments of all sizes. Xerox is
headquartered in Norwalk.This is a Support project where SAP 4.7EE version is
being used where modules like SD MM FICO with HR are being used .Integrated to
work with par HCL technologies.
Contribution:
Inbound idocs for the idoc type HRMD_A_06 and for a ‘z’ message type
that can handle the HR master data from HRPCLNT700 to XHPCLNT400 .
Inbound as well as Outbound idocs with an external Finance production
system with the HR Payroll system at client production environment .
Involved in setting the Partner profiles with respect to finance and HR payroll
system and also with the actual HR Master data server located.
Involved in maintaining the Distribution model across the sending and
receiving Logical systems Standard process code HRMD used for Inbound
and BAPI process code used for outbound idocs and respective standard
function modules got involved in processing idocs.
Involved in monitoring the idocs and finding the error idocs while Serialization
Error occurs.
Involved in reprocessing of the error idocs manually ( BD87 ) .
Background jobs ( RBDMANI2 with different variants saved one for Great
Britain and Ireland
1. Project Name : BBC
Client BBC
Role Team Member
Organization SISPL, India
Duration 02/2010 – 07/2010
Team Size Project : 40 Module : 15
Environment Software Languages : ABAP
(with skill versions) Database : Oracle
Tools :-
O/s : Windows XP
Project Description
People view project is mainly projected with the enhancement and support of all the
affected programs which are intended to use NAKISA software that demands the
change in Org Structure in HR module and support for the client
Contribution:
Involved in making changes to necessary reports interfaces and forms that
are bound to be changed with the involvement of new HR software by name
NAKISA
SAP Workflow sends the PO for approval to the approver depending on the
release code. This process consists of 4 workflows that are based on these
events (Release step created, changed, resend, reset)
Freelancer Contract Request Workflow for the create event in the Z’ BOR
after approval the freelancers are hired using a z program.
PO workflow where in ,based on the PO amount the responsible Agent will
be assigned and act on PO
The workflow automatically creates GRN (Goods Receipt Number) through a
999BDC for MB01 (Material Document Create) for the PO (Purchase Order)