Data Analyst Analysis

DURGA DEVENDLA

* **** **** **** *** ** Plymouth MA 02360 +1-661-***-****

***************@*****.***

Certifications:

EDUCATION

Master of Science in Computer Science May 2024

Rivier University, Nashua, New Hampshire

Bachelor Of Engineering in Computer Science Aug 2016

Sri Indu College of Engineering and Technology, Hyderabad, India

TECHNICAL SKILLS

Databases: MySQL, MongoDB, PostgreSQL, Oracle PL/SQL, MS Access

Big Data Technologies: Apache Hadoop (HDFS/MapReduce), PIG, HIVE, HBASE, SQOOP, FLUME, OOZIE

Web Technologies : JSP. JDBC, HTML, JavaScript

Languages: JAVA, Python, R Programming, PySpark

Machine Learning / Data Analysis / Statistics: Hidden Markov Model, Random Forest, Decision Tree, Support Vector Machine, Neural Network

Operating Systems: Windows, UNIX, and Linux

Frame Works: Spring, Hibernate

Version Control: VSS (Visual Source Safe), CVS

Agile Methodology: Jira

Visualization Tools: Tabeau, Power BI

Cloud: AWS, Snowflake

Data Analyst Intern – HI-MY-LINK, San Francisco, CA, USA

January 2023 - Present

Evaluated business requirements and prepared detailed specifications that follow project guidelines required to

develop written programs.

Created an aggregated report daily for the client to make investment decisions and help analyze market trends.

Built an internal visualization platform for the clients to view historic data. make comparisons between various issuers analytics for different bonds and market.

Built the model on Azure platform using Python and Spark for the model development and Dash by plotly for visualizations.

Built REST APIs to easily add new analytics or issuers into the model.

Automate different workflows, which are initiated manually with Python scripts and Unix shell scripting.

Write Python scripts to parse JSON documents and load the data in database

Generating various capacity planning reports (graphical) using Python packages like Numpy, matplotlib.

Analyzing various logs that are been generating and predicting/forecasting next occurrence of event with various Python libraries.

Created Autosys batch processes to fully automate the model to pick the latest as well as the best bond that fits best for that market.

Created a framework using plotly, dash and flask for visualizing the trends and understanding.

Used python APs for extracting daily data from multiple vendors.

Used Spark and SparkSQL for data integrations manipulations Worked on a POC for Creating a docker image on azure to run the model.

Built an FCN from scratch which will segment the image pixel to pixel on GPU with an accuracy of 89.2% on cloud using Image Segmentation with Fully Convolutional Networks with Python, Keras, TensorFlow, Python, Colab.

Environment: Hadoop 3.0, MapReduce, Hive 3.0, Agile, HBase 1.2, NoSQL, PySpark, Autosys, Plotly, Spark, PL/SQL, Python, Jenkins.

Senior Data Analyst – Valley INFOSYSTEMS PVT LTD, Bangalore, India

May 2020 – June 2022

Evaluated business requirements and prepared detailed specifications that follow project guidelines required to develop written programs.

Loaded and transformed large sets of structured, semi structured, and unstructured data using Hadoop/Big Data concepts.

Implemented Data Exploration to analyze patterns and to select features using Python Scipy.

Built Factor Analysis and Cluster Analysis models using Python SciPy to classify customers into different target groups.

Supported MapReduce Programs running on the cluster.

Participated in Data Acquisition with Data Engineer team to extract historical and real time data by using Hadoop MapReduce and HDFS.

The model collects, merges daily data from market providers and applies different cleaning techniques to eliminate bad data points.

The model merges the daily data with the historical data and applies various quantitative algorithms to check the best fit for the day.

Captures the changes for each market to create a daily email alert to the client to help make better investment decisions.

Communicated and presented default customers profiles along with reports using Python and Tableau, analytical results, and strategic implications to senior management for strategic decision making.

Developed multiple MapReduce jobs in java for data cleaning and pre-processing.

Analyzed the partitioned and bucketed data and compute various metrics for reporting. Extracted data from Twitter using Java and Twitter API.

Worked on Dimensional Data modelling in Star and Snowflake schemas and Slowly Changing Dimensions (SCD)

Prepared Scripts in Python and Shell for Automation of administration tasks.

Maintained PL/SQL objects like packages, triggers, procedures etc.

Mapping flow of trade cycle data from source to target and documenting the same.

Environment: Pig 0.17, Hive 2.3, HBase 1.2, HDFS, Cloudera, Scala, Spark 2.3, SQL, python, Tableau, Git, Jira.

Associate Data Analyst – Valley INFOSYSTEMS PVT LTD, Bangalore, India

October 2016 – April 2020

Contributing to the development of key data integration and advanced analytics solutions leveraging Apache Hadoop and other big data technologies for leading organizations using major Hadoop Distributions like Hortonworks.

Involved in Agile methodologies, daily Scrum meetings, Sprint planning.

Extensively used Python's multiple data science packages like Pandas, NumPy, matplotlib, Seaborn, SciPy, Scikit- learn and NLTK.

Performed Exploratory Data Analysis, trying to find trends and clusters.

Built models using techniques like Regression, Tree based ensemble methods, Time Series forecasting, KN, Clustering and Isolation Forest methods.

Worked on data that was a combination of unstructured and structured data from multiple sources and automated the cleaning using Python scripts.

Used Python to preprocess data and attempt to find insights.

Iteratively rebuild models dealing with changes in data and refining them over time.

Created and published multiple dashboards and reports using Tableau server.

Extensively used SQL queries for legacy data retrieval jobs.

Tasked with migrating the Django database from MySQL to PostgreSQL.

Used big data tools Spark (Spark SQL, Mllib) to conduct the real time analysis of credit card fraud based on aws

cloud and Performed Data audit, QA of SAS code/projects and sense check of results.

Environment: Spark, Hadoop, AWS, SAS Enterprise Guide, Python (scikit-learn, pandas, Numpy), Machine Learning (logistic regression, XGBoost), Gradient Descent algorithm, Bayesian optimization

ACADEMIC PROJECTS:

Emotion recognition within e-learning platforms:

emotion recognition within e-learning platforms to determine how accurately emotions can be identified through learners' interactions and responses so that others can better understand how to tailor educational experiences to improve engagement and learning outcomes.

Deep Learning for Image Recognition:

Achieved breakthrough accuracy in brand logo detection within images sourced from social media, enhancing brand monitoring efforts.

Implemented real-time image processing for live event coverage, facilitating instant content categorization and tagging.

Conducted comparative studies on model performance across different datasets, optimizing model architecture for generalized applications.

AI-Driven Market Basket Analysis:

Enabled personalized marketing by uncovering intricate product association rules, leading to a 20% uplift in cross-selling opportunities.

Applied the analysis to optimize store layout and product placement, contributing to a 5% increase in overall sales.

Integrated findings into the e-commerce platform's recommendation engine, significantly improving user experience and satisfaction.

Natural Language Processing for Social Media Analytics:

Expanded the NLP model to support multiple languages, increasing the tool's applicability for global brands.

Incorporated sentiment intensity analysis to distinguish between mild and strong sentiments.

Developed a dashboard for visualizing sentiment trends over time, aiding in marketing campaign adjustments.

Machine Learning for Healthcare: Predictive Diagnostics

Integrated electronic health records (EHR) data with the model to enhance diagnostic accuracy.

Collaborated with healthcare professionals to tailor the model for specific disease predictions.

Conducted a validation study, demonstrating the model's potential to reduce diagnostic errors by 25%.

Reinforcement Learning for Stock Market Prediction:

Applied advanced reinforcement learning techniques to adapt the model to volatile market conditions.

Tested the model with historical data from multiple stock exchanges to ensure its robustness and scalability.

Developed a user-friendly interface for traders to input parameters and receive predictions and trading signals.

Contact this candidate