Data Analytics Analyst

Poojitha Pakeeru

623-***-**** ad5mt0@r.postjobfree.com linkedin.com/in/poojitha github.com/Pakeeru San Diego, CA Education

San Diego State University Aug 2022 – May 2024

Master of Science in Big Data Analytics, GPA:3.82/4.00 San Diego, CA Jawaharlal Nehru Technological University Aug 2017 – May 2021 Bachelor of Technology in Electronics and Communication Engineering, GPA: 3.92/4.00 Hyderabad, India Experience

Data Analyst Aug 2022 – Present

San Diego State University San Diego, CA

• Constructed dashboards for insights and data visualization after extracting data from SDSU EAB Navigate using Microsoft Excel, Tableau, and Matplotlib, resulting in streamlined reporting to the Dean of Engineering.

• Evaluated data encompassing the overall student population at COEng SDSU, consisting of 5000+ students with 7+ majors, to support strategic planning, identify KPI’s, perform root cause analysis and resource allocation within the Supply Chain.

• Enhanced advising processes at CSSE through Agile, Lean, and Six Sigma methodologies, increasing efficiency by 15%. Data Analytics Engineer Aug 2021 – Aug 2022

Accenture Hyderabad, India

• Spearheaded the development of dashboards and comprehensive reports utilizing SSRS, Python scripts, Thoughtspot, Tableau, and QlikView, enhancing clarity and efficiency in presenting HR data analytics with respect to financial data to management and stakeholders.

• Orchestrated the deployment of SSIS packages to facilitate an efficient ETL pipeline for data, resulting in a 20% enhancement in overall data warehouse quality.

• Led integration of advanced Natural Language Processing (NLP) particularly employing Word Embeddings, Recurrent Neural Networks (RNNs), and Large Language Models (LLMs) for Accenture’s chatbots DiPA and Ava, achieving a 13% cut in customer support inquiries. Facilitated on-the-go access to a range of HR functions, such as onboarding and payroll across all entities. Data Engineer Intern Feb 21 – July 21

Cognizant Hyderabad, India

• Concluded a 6-month training program by developing SQL logic queries for aggregate views using MySQL Workbench and AWS-RDS database, efficiently managing and extracting insights from a substantial 1TB dataset.

• Detailed data governance requirements, leveraged Python, Apache Spark and AWS services (S3, Amazon Glue - ETL processes) to automate tasks and achieve a 30% reduction in data processing time. Data Scientist Intern May 2020 – Aug 2020

Moksha IT Consulting Hyderabad, India

• Engineered and deployed Gradient Boosting Machines (GBM) and Random Forest algorithms for Business Data Analysis, enabling the efficient handling of 7000+ policy records daily.

• Leveraged Python’s TensorFlow and Keras libraries to construct and fine-tune LSTM networks and GBM models. Improving predictive accuracy, yielding a 20% increase in user engagement within a span of 6 months.

• Implemented statistical methods such as A/B tests, T-test, regression, ANOVA, and Hypothesis Testing ensuring results have statistical significance, which led to a 15% increase in the reliability and accuracy of data-driven insights. Projects

UrbanVoyage Python, PostgreSQL, Docker, Lucid Charts (Data Models, Flow Diagrams), Visual Studio, Git Feb 2024 – Present

• Led a data engineering project on GCP, processing over 10 years of diverse NYC taxi data across three categories. Deployed an efficient ETL pipeline, utilized BigQuery for analysis, and implemented Looker for insightful dashboards. Anomaly Detection from Time-Series MIT-BIH ECG Dataset Seaborn, Scikit, Tslearn Aug 2023 – Dec 2023

• Detected cardiac irregularities in 48 ECGs using unsupervised learning techniques( K-means, Fuzzy C-means, Isolation Forest), improved precision with majority voting method, and unveiled temporal patterns in 30-minute ECG records. Analyzing Hashtags & Trends of Twitter during Covid-19 ArcGIS, Textblob, VBA Aug 2022 – Dec 2022

• Revitalized Twitter analysis with Tableau, executing Sentiment Analysis, Text Clustering (8 clusters), and Spatial Analysis. Applied Topic Modeling to pinpoint 8 topics, extracting trends correlating real-world events with hashtags for dashboards. SKILLS

Programming Languages Python, R, Java, SQL (Postgres), JavaScript, HTML/CSS Frameworks Pandas, scikit-learn, TensorFlow, Keras, PyTorch, NLTK, Django, FastAPI, Pytorch, Hugging Face Tools Excel, PowerBI, ArcGIS, Hadoop, Spark, Hive, Jira, Git, Informatica DQ, Docker, Visual Studio, Selenium Database OLAP, OLTP, MySQL, PostgreSQL, MongoDB, Google BigTable Cloud Technologies AWS(Redshift, EC2 Ultraclusters, SageMaker), Azure, GCP,Snowflake, Databricks

Contact this candidate