Priyanka Rasakonda

Developed a deep learning model using convolutional neural networks (CNNs) and utilized U-Net architecture for accurate segmentation.
Implemented the project using Python, TensorFlow, and Keras for model development and training.
Implemented and evaluated generative models, large language models, and transformer-based deep neural networks.
Tokenized sentences, lemmatized words, and created a bag-of-words representation for each sentence to prepare the data for model training.
Developed and trained a neural network model using Keras Sequential API.
Defined the model's architecture with multiple dense layers and dropout regularization.
Used SGD as the optimizer and categorical cross-entropy as the loss function for training the model.
Monitored the training process, analyzed performance metrics, and fine-tuned hyperparameters to optimize the model's performance.
Evaluated the trained model's performance using validation techniques such as cross-validation or train-test splits.
Calculated evaluation metrics such as accuracy, precision, recall, and F1-score to assess the model's effectiveness in predicting intents accurately.
Integrated speech recognition functionality into the chatbot to recognize speech input from users.
Implemented text-to-speech conversion to generate spoken responses from the chatbot.
Assisted in the development and testing of chatbot prototypes, including data collection, preprocessing, and model training.
Conducted literature reviews and research on NLP techniques, algorithms, and emerging trends in chatbot development.
Participated in team meetings and brainstorming sessions to discuss project goals, milestones, and deliverables.
Contributed to the creation of technical documentation, including code repositories, user guides, and API documentation.
Demonstrated strong problem-solving and critical thinking skills by analyzing complex data sets and developing innovative solutions to enhance model accuracy and business outcomes.
Presented findings and project updates to stakeholders, including managers, developers, and business users.
Provided technical expertise and training to team members on NLP concepts, methodologies, and best practices.
Successfully deployed the chatbot application, enhancing the user experience and efficiency in accessing IT support services.
Experience in working with Twilio, Dialog Flow, and knowledge about Rasa chatbot development.
Implemented routes and endpoints to handle user requests and return chatbot responses in JSON format.
Ensured seamless integration of the chatbot functionality within the web application for a smooth user experience.

Implemented CI/CD pipelines using Google Cloud Build for automated deployment of microservices.
Developed and maintained interactive dashboards in Tableau and PowerBI to visualize player engagement, in-game purchases, and churn rates, providing valuable insights for game design enhancements.
Utilized Python for predictive modelling, identifying potential areas for in-game purchases and implementing personalized offers, which led to a 15% increase in revenue.
Regularly presented findings to executives and game designers, influencing game feature decisions based on data insights.
Applied natural language processing (NLP) techniques to analyze customer reviews and feedback, identifying key areas for product improvement.
Leveraged SQL to query and analyze large datasets, providing valuable insights into player demographics and preferences.
Migrated on-premises infrastructure to GCP, resulting in a 30% reduction in infrastructure costs.
Optimized GCP resources to improve performance and reduce costs.
Developed and implemented data preprocessing and feature engineering pipelines for predictive modeling projects, ensuring data quality and enhancing model performance.
Conducted exploratory data analysis (EDA) to identify trends using Tableau and Python (Matplotlib, Seaborn, Plotly Dash).
Leveraged data-driven decision making and quantitative analysis to support strategic business decisions and optimize operational processes.
Managed and deployed machine learning models using Kubernetes, enabling scalable and resilient models in production environments.
Presented findings and recommendations to senior management, influencing strategic decisions based on data-driven insights.
Gained extensive experience in project management and documentation using JIRA and Confluence.
Participated in code reviews and contributed to the development of best practices for data science workflows.

Collaborated with cross-functional game development teams to define and analyze key game performance metrics, leading to data-informed updates and improvements.
Assisted in the development of data collection strategies to gather user interaction data for analysis.
Collaborated with senior data analysts to identify key performance indicators (KPIs) for game mechanics evaluation.
Worked closely with the development team to implement data-driven design changes based on user feedback and data analysis.
Designed and developed interactive dashboards using AWS Quick Sight, providing insights into invoice volumes, processing times, and payment status.
Implemented ETL processes to automate data refresh and maintain data integrity and consistency.
Conducted exploratory data analysis (EDA) on player behavior data to identify patterns and trends.
Contributed to the creation of data visualizations and dashboards to communicate insights to team members.
Participated in user acceptance testing (UAT) to validate the functionality of new game features and ensure a seamless user experience.
Contributed to the improvement of the testing process by providing feedback and suggestions for optimizing testing procedures.