Required Skills

SCALA SPARK SQL Data Science

Work Authorization

  • Us Citizen

  • Green Card

  • EAD (OPT/CPT/GC/H4)

  • H1B Work Permit

Preferred Employment

  • Corp-Corp

Employment Type

  • Consulting/Contract

education qualification

  • UG :- - Not Required

  • PG :- - Not Required

Other Information

  • No of position :- ( 1 )

  • Post :- 9th Jan 2021

JOB DETAIL

Role: Sr Data Scientist 
Location: Irving, TX
Duration: Long term

Candidate should have 10-12+ years relevant experience & 5+ years in Data Science

Job Description
Responsible for developing strategies for effective data analysis and reporting. Selects, configures, and implements analytical solutions. Develops and implements data analytics, data collection systems, and other strategies that optimize statistical efficiency and quality. Identifies, analyzes, and interprets trends or patterns in complex data sets.
Manages computer systems in a business environment and responsible for resolving technical issues. Knowledgeable in programming, data structures, computer systems, and software engineering. Bachelor's or Master's degree in computer science, software engineering, or other related field. Ability to manage multiple assignments. Superior written and oral communication skills. 10-12+ years of experience.

Requirement:
- Strong Background in Predictive Analytics, Machine Learning, Consulting Reporting and
Business Development
- Worked on various modelling techniques like Linear Regression, Logistic Regression
(Binomial and Multi-Class), Robust Regression, DBSCAN, Text Analytics (NLP), 3
Dimensional Tensor Factorization, Time-Series Analysis, Clustering, Holt-Winters
Forecasting Technique, Decision Tree Analysis, Boosted Decision Tree Analysis, CNNs like
Resnet, Inception etc.
- Has an overall experience of 6- 12 years and worked on wide array of domains such as
Telecom, Networking, Healthcare (Payer & Provider) , Pharmaceuticals and Supply Chain
- Experience on data manipulation and various statistical techniques and tools such as SAS
- Proven understanding and related experience with Hadoop, HBase, Hive, Pig, Sqoop, Flume, Hbase, Map/Reduce, Apache Spark as well as Unix OS Core Java programming, Scala, shell scripting experience.
- Solid experience in writing SQL, stored procedures, query performance tuning preferably on Oracle 12c.

Responsibilities:
Development of the System of Insights platform
- Analysed various data sources like online, call center, chat, notifications,
network, social media, sales etc. to create a unified view which helps in
generating multiple propensity scores
- Determine factors and predict the possibility of customer repeat visit to the store
to create a logistic regression to determine the important factors and predict the possible time frame in which a customer would revisit
- Root Cause Analysis of Network Logs
- Design the algorithm to generate Log Templates from normal Log Messages
Optimized the Template generation process through use of SCALA, SPARK
cluster to process logs faster.
- Design a Tensor Factorization algorithm in R to optimize the log template
patterns existing in the network logs
- Design of new Algorithm in R to handle 3 Dimensional Network Data
- Design and Develop Customized Multistage Control Charts in R
Defined and developed the metrics to calculate success rates across various
channels available for each individual
- Identify channel and influence of other factors like activities on the success and
failure of the self-service
- Develop a predictive model to determine the Diagnosis, Demographic and
lifestyle factors.
- Anomaly Detection using Analytics
- Define and develop key criteria for detecting anomalies in the data
Statistical modeling to predict the degree of accuracy of the data
- Forecast the sales for various products across various locations for the client

EDUCATION/CERTIFICATIONS:
Bachelor's/Masters in Computer Engineering or Information Technology
Hadoop and AIML Certification is added advantage

Company Information