Revathi B Pathuri
Columbus
Summary
Meticulous Data Scientist with 10 years of experience accomplished in compiling, transforming and analyzing complex information through Algorithms. Expert in machine learning and large dataset management. Demonstrated success in identifying relationships and building solutions to business problems.
Overview
13
13
years of professional experience
1
1
Certification
Work History
Scientific Content Engineer (NLP Lead)
CAS
06.2023 - Current
- Conducted a comparative performance evaluation of two distinct models, one based on Natural Language Processing (NLP) techniques and the other on traditional Machine Learning approaches, to achieve efficient information extraction. Employed rigorous experimentation and analysis to quantify the accuracy, precision, recall, and F1-score of each model. Results informed data-driven decisions and optimizations for enhancing information extraction processes
- Led a comprehensive project focused on extracting intricate Drug-Target Relationship data from diverse biomedical literature sources. Leveraged advanced Natural Language Processing (NLP) techniques to parse, classify, and extract key information, facilitating the identification of potential drug candidates and their corresponding target proteins. Developed and fine-tuned custom NLP pipelines, including entity recognition and relation extraction, achieving an X% increase in precision and recall compared to baseline methods. The successful implementation of this project contributed valuable insights to drug discovery efforts and exemplified proficiency in NLP-driven information extraction
Senior Data Scientist
Macy's
01.2023 - 05.2023
- Developed an algorithm to predict the demand of products of various departments based on the historical sales data to improve the profit by stock maintenance.
- Preparing data using techniques like dimensionality reduction for reduction of features using (PCA, t-SNE) , cleaning the data using libraries of Python.
- Applying advanced statistical techniques (Bayesian, sampling and experimental design) while performing machine learning algorithms on the heterogenous data.
- Used advanced analytical tools and programming languages such as Python (NumPy, pandas, SciPy) for data analysis.
- Constructed and evaluated various types of datasets by performing machine learning models using algorithms and statistical modeling techniques such as clustering, classification, regression, decision trees, support vector machines, anomaly detection, sequential pattern discovery, and text mining from Python libraries (scikits.learn).
- Performing predictive analytics and machine learning algorithms especially supervised (SVM, Logistic Regression, Boosting), unsupervised (K-Means, LDA, EM) and Reinforcement learning (Random Forests) methods.
- Using regularization techniques to solve the over-fitting problem by reducing loss function either by adding multiple (LASSO or Ridge) or by performing cross validation.
- Create and manage data storage solutions using GCP services such as BigQuery, Cloud Storage, and Cloud SQL
- Build and deploy machine learning models using GCP's AI Platform and TensorFlow
- Deployed Spark Ecosystem includes Spark SQL, pySpark DataFrames
- Experience with migrating other databases to snowflake
- Experience with Snowflake cloud technology, snowflake cloud data warehouse and AWS S3 bucket for integrating multiple source system which include loading nested JSON data format in to snowflake table
- write complex snowsql in snowflake cloud data warehouse business analysis and reporting
- Trained and led junior data scientists with appropriate tool for specific problems.
Data Scientist
Bosch Rexroth
09.2018 - 10.2021
- Achieved prediction of failures from historical machine data using Anomaly detection, Feature selection
- Managed implementation of new features by outlining plans and specifications such as how, where and when each component would work.
- Neural Network techniques such as logistic regression, K- Nearest Neighbor algorithms were implemented as well for enhancing the accuracy rates in prediction failure model
- Created in house database (OLAP) to process and analyze the data
- Explored the data to obtain time real-time insights
- For analysis, hierarchal clustering algorithm was implemented which in this process enabled grouping of similar data points
- It helped us understand a group of malfunctioning of machine parts or change in the level of certain contents like iron, copper etc., which eventually lead to the failure of the machine
- Saved 400K $ from the failure of machine and the faulty function of the machine for the potential customers
- Created efficient data visualization UI using Tableau to showcase the abnormalities and the cause of failure in data
- The machine learning model is written using python and the database is accessed using SQL.
Junior Data Scientist
Robert Bosch GmbH
10.2017 - 04.2018
- Built models using supervised classification techniques like K-Nearest Neighbor (KNN), Logistic Regression and Random Forests with Principal component analysis to identify important features
- Performed Exploratory Data Analysis (EDA) to maximize insight into the dataset, detect the outliers and extract important variables numerically and graphically.
- Worked with Hadoop Ecosystem covering HDFS, HBase, YARN and MapReduce.
- Built advanced Machine Learning classification models like KNN , SVR and clustering algorithms Hierarchical Clustering.
- Used K-Means Algorithm Model with different clusters to find meaningful segments on customers and calculated the accuracy of model.
- Performed data mining on data using very complex SQL queries and discovered pattern and used extensive SQL for data profiling/analysis to provide guidance in building the data model.
- Used Python, SQL to create Statistical algorithms involving Multivariate Regression, Linear Regression, Logistic Regression, PCA, Random Forest models, Decision trees, Support Vector Machine for estimating the risks.
- Involved in creating Data Lake by extracting customer's Big Data from various data sources (from Excel, Flat Files, Oracle, SQL Server, Mongo DB, HBase, Teradata and log data from servers) into Hadoop HDFS.
- Created dashboards in Tableau desktop based on the data collected from MS-excel and CSV files, with MS SQL server databases.
Data Scientist Intern
SAP Germany, DE, Global Retail Services
03.2017 - 07.2017
- Created Alexa skill set and established utterances and intent schema to interact with SAP HANA database
- Performed Sentimental analysis in NLP on the email feedback of the customers to determine the tone behind the series of words by Neural Networks techniques like Long-Short Term Memory (LSTM) cells in Recurrent Neural Networks (RNN)
- Used Long-Short Term Memory (LSTM) for analyzing time series data in PyTorch
- Utilized t-Stochastic Neighborhood Embedding (t-SNE) and Principal Component Analysis (PCA) and to deal with curse of dimensionality
- Performed data visualization using various libraries and designed dashboards with Tableau, generated complex reports, including charts, summaries, and graphs to interpret the findings to the team and stakeholders.
Research Assistant
DFKI, German Research Center of AI
08.2014 - 06.2016
- Automated the calculation of demanded dates with the help of machine learning
- Built advanced Machine Learning classification models like KNN, SVM Regression and clustering algorithms Hierarchical Clustering and DBSCAN
- Developed NLP with Deep Learning algorithms for analyzing text improving over their existing dictionary-based approaches
- Worked on Natural Language Processing and extracted data from multilingual hotel invoices
- Extracted data from social media platforms such as Facebook, twitter and Google using prebuilt social media API
- Hands on experience in Working with the large volume of data with more than 10M customer records with 20+ features
Assistant Systems Engineer - Hadoop Developer
Tata Consultancy Services
01.2012 - 12.2013
- Proficient in Cloudera distribution for Hadoop, including Cloudera Manager and Cloudera Navigator.
- Familiarity with Big Data tools such as Hadoop, MapReduce, Hive, Pig, Kafka, and Python.
- Implemented a scalable and fault-tolerant data processing pipeline using Cloudera and Apache Spark, resulting in a 30% reduction in processing time.
- Utilized Spark's machine learning libraries (MLlib) to build predictive models for customer segmentation, resulting in a 20% improvement in targeted marketing campaigns.
- Developed a custom data ingestion framework using Spark and Scala, reducing data loading time by 40% and enhancing data quality.
- Presented technical workshops and training sessions on Cloudera, HBase, and Spark for internal teams, enhancing their understanding and adoption of Big Data technologies.
- Performed data visualization using various libraries and designed dashboards with Tableau, generated complex reports, including charts, summaries, and graphs to interpret the findings to the team and stakeholders
- Developed Oozie Workflows for daily incremental loads to get data from social media and imported them into Hive tables
- Resolved classification algorithms such as Linear Regression, Logistic Regression, and K-NN to predict the customer churn and customer interface
- Built models using supervised classification techniques like K-Nearest Neighbor (KNN), Logistic Regression and Random Forests with Principal component analysis to identify important features
- Used Jupyter notebook for writing Python scripts for training/testing data sets.
Education
Master of Science - Artificial intelligence
Technical University of Kaiserslautern
Germany04.2018
Bachelor of Science - Computer Science
Kalasalingam University
India04.2011
Skills
- Data Visualization
- Predictive Analysis
- Statistical Modelling
- Data Analytics
- Clustering and Mining
- Data Mining
- Logistic Regression
- Linear Regression
- Support Vector Machine
- Decision Trees
- K-Nearest Neighbor
- Naïve Bayes
- K- Means Clustering
- Hierarchal Clustering
- Density Based Clustering
- Principal Component Analysis
- Natural Language processing
- Artificial Neural Networks
- Recurrent Neural Networks
- Model development
- Quantitative Analysis
- Deep Learning
- Machine Learning
- Demand Forecasting
- Business Intelligence
- Data Modelling
- Market Trend Analysis
- Jupyter Notebook
- Gradient Boosting
- Time Series Models
Additional Information
- Awarded Math Excellency 2008
- Best outgoing student of the year 2009-2010
Certification
IBM Applied AI Professional Certificate
Coursera certified Hadoop Developer
IBM Rational Functional Tester
Timeline
Scientific Content Engineer (NLP Lead)
CAS
06.2023 - Current
Senior Data Scientist
Macy's
01.2023 - 05.2023
Data Scientist
Bosch Rexroth
09.2018 - 10.2021
Junior Data Scientist
Robert Bosch GmbH
10.2017 - 04.2018
Data Scientist Intern
SAP Germany, DE, Global Retail Services
03.2017 - 07.2017
Research Assistant
DFKI, German Research Center of AI
08.2014 - 06.2016
Assistant Systems Engineer - Hadoop Developer
Tata Consultancy Services
01.2012 - 12.2013
Master of Science - Artificial intelligence
Technical University of Kaiserslautern
Bachelor of Science - Computer Science
Kalasalingam University
IBM Applied AI Professional Certificate
Coursera certified Hadoop Developer
IBM Rational Functional Tester
Similar Profiles
Bhupendra SubediBhupendra Subedi
Cleaning Assistant at Cas Cas Gruppen A/SCleaning Assistant at Cas Cas Gruppen A/S
Md Abdur RahimMd Abdur Rahim
Cleaner at Cas Cas GruppenCleaner at Cas Cas Gruppen
Amethyst JohnsonAmethyst Johnson
HOA Portfolio Property Manager at Associa, CAS INCHOA Portfolio Property Manager at Associa, CAS INC