Data Analyst Power Bi

Sai Sindhuja Mudadla

******************@*****.*** +1-262-***-**** http://www.linkedin.com/in/mudadlasaisindhuja Results-driven Data Analyst with 5 years of experience in business intelligence, data visualization, and predictive analytics. Proficient in Power BI, SQL, and Python, with a strong track record of transforming raw data into actionable insights that drive strategic decision-making. Skilled in data modeling, ETL processes, and DAX calculations to enhance reporting efficiency. Adept at automating workflows and optimizing SQL queries to improve operational performance. Passionate about leveraging data analytics to solve complex business problems and support organizational growth.

Summary

• Conducted 4G/5G RAN analytics using SQL, Power BI, and Python to optimize network performance and connectivity across key telecom KPIs.

• Developed advanced Power BI dashboards with DAX measures and calculated columns to track call drops, latency, and traffic trends in real-time.

• Automated end-to-end reports using Power Query and Python scripts, reducing manual effort by 30% and improving operational efficiency.

• Designed and optimized SQL queries across MySQL, PostgreSQL, and SQL Server environments to extract actionable business insights.

• Created dynamic dashboards in Tableau for customer segmentation, demographic analysis, and product trend visualization.

• Built predictive machine learning models using Scikit-learn, Random Forest, Logistic Regression, and Naïve Bayes for churn prediction and healthcare analytics.

• Enhanced model performance with hyperparameter tuning, feature selection, and cross-validation techniques.

• Designed a real-time Twitter sentiment classifier using NLP, TF-IDF, and Count Vectorizer, achieving 88% classification accuracy.

• Implemented deep learning pipelines using LSTM, CNN, Keras, and TensorFlow for fake news detection and text classification.

• Performed text preprocessing (tokenization, stopword removal, stemming) using NLTK and SpaCy, ensuring clean and contextual input data for models.

• Integrated live social media analytics into Power BI using Twitter API and real-time dashboards to monitor public sentiment.

• Developed spam detection and email filtering systems using the Enron Dataset with Naïve Bayes and Bag-of-Words models.

• Built interactive climate forecasting dashboards using Prophet, ARIMA, Pandas, and Matplotlib to identify long-term weather trends.

• Processed and transformed large-scale datasets using Pandas, NumPy, and Seaborn for EDA and model training.

• Engineered real-time data pipelines using Azure Data Factory, dbt, and Apache Airflow for scalable data ingestion and transformation.

• Leveraged cloud platforms including Microsoft Azure, AWS Redshift, Google Big Query, and Snowflake for storage, computation, and deployment.

• Collaborated with cross-functional teams to translate analytics into strategic business decisions and presented findings using Looker and Excel.

• Improved marketing ROI by 10% through K-means clustering and customer segmentation in Python integrated with Power BI visuals.

• Implemented healthcare risk models using Random Forest and Neural Networks, achieving up to 87% precision in stroke and heart disease prediction.

• Applied Git, Jupyter Notebooks, and Google Colab for reproducible, collaborative machine learning development and documentation.

Technical Skills

• Programming Languages: Java, Python, C, C++

• Web Technologies: JavaScript, HTML, CSS, Node.js, AngularJS, jQuery

• Data Science & Machine Learning: Pandas, NumPy, Matplotlib, Scikit-learn, TensorFlow, Keras, PyTorch

• Data Analysis & Visualization: Power BI, Tableau, Excel, Looker

• Databases & Programming: SQL (MySQL, PostgreSQL, SQL Server), Python (Pandas, NumPy, Matplotlib, Seaborn)

• Data Modeling & ETL: Power Query, Dataflows, DAX, Azure Data Factory, Alteryx, dbt, Apache Airflow

• Machine Learning & Statistics: Regression Analysis, Predictive Modeling, NLP, FastAPI

• Cloud & Big Data: Microsoft Azure, Google BigQuery, AWS (S3, Lambda, SageMaker, Redshift)Snowflake

• Development Tools & IDEs: Jupyter Notebook, Google Colab, PyCharm

• Soft Skills: Problem-Solving, Teamwork, Leadership, Communication. Work Experience

Invences Inc. Data Analyst (Jan 2024 – Present)

• Collected, cleaned, and analyzed 5G Standalone (SA) network data using SQL and Python for insights on latency, jitter, packet drops, and throughput.

• Designed and developed Power BI dashboards to visualize network KPIs, allowing real-time monitoring of source/destination IPs, ports, and traffic types.

• Extracted data from 5G core network components (AMF, SMF, UPF, AUSF, NRF, UDR, PCF) to support advanced analytics use cases.

• Translated complex telecom performance data into actionable business insights for non-technical stakeholders using data storytelling techniques.

• Implemented predictive analytics models in Python to forecast anomalies and optimize resource planning.

• Integrated AI-driven feedback loops into monitoring systems to automate resolution strategies (restart, terminate, migrate).

• Used DAX in Power BI to create calculated columns and measures for deeper performance insights and metric comparisons.

• Created issue heatmaps and trend reports in Power BI to support proactive decision-making and service assurance.

• Analyzed traffic flow across various protocols (TCP, UDP, HTTP, VPN) to optimize data transmission efficiency.

• Mapped 5G infrastructure layers (RU, DU, CU-CP, CU-UP, Baseband 6631) to data pipelines for end- to-end traceability.

• Correlated PLMN ID and SIM data with network events to identify patterns in private network usage.

• Monitored and reported on performance metrics across multi-vendor hardware (Dell R640/740/820, XR1000, HPE DL380/580, EL8K/9K).

• Collaborated with cross-functional teams (engineering, operations, business) to align data findings with strategic goals.

• Created automated reports using Power BI and Excel for weekly executive summaries and SLA compliance tracking.

• Participated in the development of proactive monitoring frameworks using Common DART, Cimon, and in-house observability tools.

Pc2 Scientific Solutions Data Analyst (May 2019 – December 2023)

• Analyzed business data, created detailed reports and dashboards, and ensured data accuracy and integrity across marketing and product teams.

• Assisted departments in integrating and visualizing data for consumption by stakeholders, executive leadership, and cross-functional project managers.

• Identified and validated business requirements by collaborating with non-technical stakeholders and translating them into actionable solutions.

• Organized business and technical requirements into structured documents using standardized business analysis frameworks.

• Created and maintained interactive Power BI dashboards and rich data visualizations derived from multi-source datasets.

• Integrated reporting components from diverse platforms, aligning datasets for unified business intelligence delivery.

• Managed and enhanced existing reporting systems to meet evolving needs of internal stakeholders and operational units.

• Leveraged knowledge of data capture, requirements development, and data strategy to advise leadership on analytics implementation.

• Collaborated with data engineers and reporting analysts to assess trends, generate insights, and evaluate KPIs tied to organizational initiatives.

• Provided data-driven recommendations that improved campaign performance, operational efficiency, and executive decision-making.

Academic Projects

Sentiment analysis

• Developed a real-time sentiment classification model using live Twitter data.

• Utilized Natural Language Processing (NLP) for text preprocessing and sentiment analysis.

• Applied TF-IDF and Count Vectorizer for effective feature extraction.

• Trained models using Random Forest and Naïve Bayes algorithms.

• Achieved an accuracy of 88% in sentiment classification.

• Processed and managed large Twitter datasets efficiently using Pandas.

• Created visualizations with Matplotlib and Seaborn for sentiment trends.

• Built using Python with Scikit-learn, Pandas, Matplotlib, and Seaborn.

• Designed the model for potential real-time deployment and scalability.

• Useful for brand monitoring, public sentiment analysis, and market research. Customer Segmentation

• Collected and preprocessed customer purchasing behavior data for segmentation.

• Applied K-Means clustering to group customers into distinct segments based on spending patterns.

• Identified high-value customers and potential churn risks using data-driven segmentation.

• Evaluated clustering performance using the elbow method.

• Integrated Python-based clustering results into Power BI for better visualization.

• Created dashboards to analyze customer segments by demographic and behavioral attributes.

• Provided business recommendations to target high-value customers with personalized promotions.

• Improved customer retention by identifying at-risk segments and designing targeted campaigns.

• Used SQL to retrieve transactional data and preprocess it before feeding it into the model.

• Increased marketing efficiency, leading to a 10% improvement in customer retention. Fake News Detection

• Developed an NLP-powered classification system to detect fake news.

• Utilized Kaggle’s fake news dataset for model training and evaluation.

• Applied Deep Learning techniques including LSTM and CNN for text classification.

• Implemented Logistic Regression as a baseline model for comparison.

• Improved detection accuracy by 10% over traditional machine learning models.

• Used Natural Language Toolkit (NLTK) for text preprocessing and tokenization.

• Leveraged TensorFlow for building and training deep learning models.

• Employed Scikit-learn for feature engineering and performance evaluation.

• Designed the model to enhance misinformation detection and fact-checking.

• Built using Python, integrating TensorFlow, NLTK, and Scikit-learn for efficient fake news classification.

Spam Email Detection

• Developed a classifier to distinguish between spam and non-spam emails.

• Used the Enron Email Dataset for training and evaluation.

• Applied text preprocessing techniques like tokenization, stopword removal, and stemming.

• Employed feature extraction methods including Bag of Words (BoW) and TF-IDF.

• Implemented Naïve Bayes as the primary classification algorithm.

• Achieved high accuracy in detecting spam emails using statistical modeling.

• Utilized Scikit-learn for machine learning model implementation.

• Processed and analyzed email data efficiently using Python.

• Designed the model for scalability and real-world email filtering applications.

• Provided an effective solution for email security and spam detection. Stroke Prediction

• Developed a Random Forest-based model for stroke prediction.

• Conducted feature selection to identify the most relevant predictors.

• Applied hyperparameter tuning to optimize model performance.

• Achieved 87% precision in predicting stroke occurrences.

• Utilized Python for data preprocessing and model implementation.

• Leveraged Scikit-learn for machine learning model development.

• Processed and analyzed healthcare data efficiently using Pandas.

• Designed the model for potential real-world medical applications.

• Enhanced model interpretability through feature importance analysis.

• Contributed to early stroke detection and healthcare decision-making. Predicting Heart Disease

• Conducted exploratory data analysis (EDA) to identify key cardiovascular risk factors.

• Analyzed data patterns and correlations to extract meaningful insights.

• Implemented Logistic Regression, Random Forest, and Neural Networks for risk prediction.

• Achieved 85% prediction accuracy, ensuring reliable model performance.

• Utilized Python for data preprocessing and model building.

• Applied Scikit-learn for machine learning model development and evaluation.

• Leveraged Pandas for efficient data handling and transformation.

• Used Seaborn for data visualization and feature correlation analysis.

• Optimized model performance through hyperparameter tuning and feature selection.

• Contributed to early detection and prevention of cardiovascular diseases Climate Change and Weather Prediction

• Analyzed historical climate data to identify temperature and weather trends.

• Explored long-term weather patterns and seasonal variations.

• Built time-series forecasting models including ARIMA and Prophet for climate trend prediction.

• Evaluated model performance using accuracy metrics for reliable forecasting.

• Designed interactive geographic visualizations to display regional climate variations.

• Utilized Python for data processing, model building, and analysis.

• Employed Pandas for handling large-scale climate datasets.

• Used Matplotlib for visualizing temperature and weather trends.

• Implemented Tableau for creating interactive climate dashboards.

• Provided valuable insights for climate monitoring and future trend analysis. Education

• University of North Texas, Denton, TX

Master of Science in Computer Science

• Centurion University of Technology and Management, AP, India Bachelor of Technology in Computer Science

Certificates

• Exploratory Data Analysis for Machine Learning (IBM)

• Supervised Machine Learning: Regression. (IBM)

• Supervised Machine Learning: Classification. (IBM)

• Introduction to Generative AI Learning Path. (Google Cloud)

• Frontend for Java Full Stack Development. (Coursera)

• Microsoft Certified: Power BI Data Analyst Associate Hobbies & Interests

• Enjoy practicing yoga for mindfulness.

• Exploring cooking to experiment with new cuisines.

• Engaging in painting as a creative outlet.

Contact this candidate