Ananda Datta
St Louis,MO
Summary
Highly competent data scientist with 6+ years of industry experience in handling big data and developing a wide range of innovative applications for providing impactful insights and tailored solutions to diverse business problems. Proficient with state-of-the-art data mining and data processing algorithms and building rigorous statistical and predictive models using scripting languages.
Overview
9
9
years of professional experience
Work History
Senior Data Scientist
Duetto Research Inc.
01.2023 - Current
- Demand Forecasting: Generate constrained and unconstrained demand forecasting models for providing tailored solutions, catered to specific revenue management system for each client depending on historic pattern, customer behavior, market trends, location parameters, seasonality and several other factors. These statistical and machine learning models are constructed, tested and deployed using Amazon Sagemaker.
- Pricing Optimization and Revenue Analytics: Develop pricing strategies and optimize pricing models to maximize revenue across 4000+ hotels worldwide. Analyze customer segments, market dynamics, competitor pricing and other factors to determine effective pricing strategies for the products. Use advanced analytics to evaluate revenue performance using key metrics, conduct A/B testing and analyze impact of pricing changes on revenue generation and inventory decisions.
Senior Data Scientist
Bayer
04.2018 - 01.2023
- Automation Tools: Designed several automation tools for scaled analytical capabilities across business domains in market development. These tools provide insightful analysis and visualization to generate tailored solutions in crop protection and agronomic system trials respectively. Used by stakeholders in Europe, Asia-Pacific and North America for analyzing 5000+ protocols involving 300,000 statistical analysis and automated report generation every year for multiple crops across multiple traits.
- Statistical Analytics: Provided comprehensive statistical analysis leading to recommendations for addressing complex business problems. Applied state-of-the-art analytical methods to evaluate factors impacting growth and profitability across product and service offerings.
- Predictive Modelling: Designed machine learning models for two projects, using SciKit-Learn in Python. First one for predicting precise herbicide formulation using various agronomic and field attributes and the second one for recommending which agronomic features would result in yield lift.
- Product Placement Algorithm: Designed a multivariate statistical analytics workflow which got embedded into the Climate FieldView digital platform. This analytics tool helps farmers to have optimal seeding density recommendation for their chosen corn hybrid and yield environment. Used across North America and Europe for more than 500,000 fields.
Applied Statistician
The Climate Corporation
06.2017 - 04.2018
- Hybrid Recommendation Model: Developed analytical models which help provide recommendation for location specific top performing hybrids using field and hybrid specific attributes. Also gives optimal yield predictions at various densities for the given hybrid-field combination.
- Predictive Model: Designed a decision tree-based machine learning model to identify which farmers will have a potential lift or no-lift based on historical yield, present static seeding rate and yield environment.
- Analytical Insights: Generated analytical insights for business recommendations for various experimental designs and field layouts.
Postdoctoral Research Scholar
Washington University School Of Medicine
10.2016 - 05.2017
- TCGA Datahub: Created a TCGA (The Cancer Genome Atlas) datahub and displayed tracks on Washington University Epigenome browser containing 1458 data tracks for 4 different cancer types for paired data.
- NIH Grant: Contributed an entire section for National Institute of Health (NIH) RO1 grant for WashU Epigenome Browser. Grant got accepted.
Education
Ph.D. - Statistics
The University of Texas At Dallas
Richardson, TX08.2016
Master of Science - Mathematics And Statistics
University of Louisiana At Lafayette
Lafayette, LA05.2011
Master of Science - Mathematics And Computing
Indian Institute of Technology
India05.2004
Bachelor of Science - Mathematics And Computing
Indian Institute of Technology
India05.2002
Skills
- Statistical analysis
- Data Mining
- Machine learning
- Big Data
- Statistical modelling
- A/B Testing
- Predictive modelling
- Data Analysis and Visualization
- Time Series Forecasting
- Project Coordination
- Testing procedures and modules
- Programming Languages: Python, R, SQL, C, C, Unix/Linux shell, Minitab, WinBUGS, MATLAB, Javascript, HTML, Fortran 95, Objective C, Core JAVA
- Tools: Amazon Sagemaker, GCP, AWS, Domino Datalab, RStudio, Jupyter Labs, Apache Spark, Amazon Redshift, BigQuery, Spotfire, Bitbucket, GitHub, DataRobot, Emacs, Eclipse
Accomplishments
Received Top Performance Award in 2019 and 2021 from leadership for spearheading trial analysis automation in Europe for seed and traits and North America for crop protection.
Publications
- Title: Comparison of haplotype-based statistical tests for disease association with rare and common variants. Authors: Ananda S Datta, Swati Biswas. Journal: Briefings in Bioinformatics
- Title: Association of rare haplotypes on ULK4 and MAP4 genes with hypertension. Authors: Ananda S Datta, Yuan Zhang, Lei Zhang, Swati Biswas. Journal: BMC Proceedings
- Title: A Family-Based Rare Haplotype Association Method for Quantitative Traits Authors: Ananda S Datta, Shili Lin, Swati Biswas Journal: Human Heredity
Journal Review
- Communications in Statistics
- Frontiers In Genetics
- MDPI Mathematics
- MDPI Sensors
- MDPI Diagnostics
- MDPI Information
Invited Talks
- Department of Mathematical Sciences, The University of Texas at Dallas (May 2022)
- School of Natural Sciences and Mathematics, The University of Texas at Dallas (August 2022)
- Chaifetz School of Business, Saint Louis University (August 2023)
- College of Arts and Sciences, Maryville University (September 2023)
Timeline
Senior Data Scientist
Duetto Research Inc.
01.2023 - Current
Senior Data Scientist
Bayer
04.2018 - 01.2023
Applied Statistician
The Climate Corporation
06.2017 - 04.2018
Postdoctoral Research Scholar
Washington University School Of Medicine
10.2016 - 05.2017
Ph.D. - Statistics
The University of Texas At Dallas
Master of Science - Mathematics And Statistics
University of Louisiana At Lafayette
Master of Science - Mathematics And Computing
Indian Institute of Technology
Bachelor of Science - Mathematics And Computing
Indian Institute of Technology
Similar Profiles
Mehrshad RafieiMehrshad Rafiei
Principal Member of Technical Staff (Tech Lead) at Duetto ResearchPrincipal Member of Technical Staff (Tech Lead) at Duetto Research
Dawn MALYDawn MALY
DSP at DuettoDSP at Duetto
Julia MeiraJulia Meira
Production Assistant at Duetto Marketing EventsProduction Assistant at Duetto Marketing Events
Gabriel SauerGabriel Sauer
Mosquito Technician at Mosquito JoeMosquito Technician at Mosquito Joe
John SchraderJohn Schrader
Senior Director at Cushman & WakefieldSenior Director at Cushman & Wakefield