Lohith Prasanna Teja Kakumanu

Data Scientist and BI Engineer

Lohith Prasanna Teja Kakumanu

Hello!

About Me

I am a passionate Data Scientist and BI Engineer with a robust technical foundation in data science and analytics. My journey in the tech world began with a strong interest in data and its potential to drive business decisions. Over the years, I have honed my skills in various domains, including data analysis, machine learning, and business intelligence. I strive to stay abreast of the latest trends and technologies to provide innovative solutions that can transform business operations and enhance decision-making processes.

Beyond my professional life, I enjoy playing the piano, which helps me relax and unwind. I also love hiking and exploring nature, which keeps me energized and inspired.

Hands-on industry-level projects and personal projects(shown in later sections) driven by my interests have given me the confidence to apply data science solutions to various problem scenarios across multiple domains such as supply chain, time series analysis, healthcare, finance, and more. The insights gained from these projects have enabled me to tackle complex business challenges and contribute effectively to organizational success.

Skills

Python

Python

Python is used for data analysis, machine learning, and automation. It's versatile and has a large ecosystem of libraries.

R

R

R is used for statistical analysis and data visualization. It excels in bioinformatics and exploratory data analysis.

SQL

SQL

SQL is used to manage and query relational databases. It's essential for handling large datasets and performing complex queries.

Java

Java

Java is used for building scalable and high-performance applications. It's known for its portability and extensive libraries.

EDA

EDA

Exploratory Data Analysis (EDA) helps in understanding the data and uncovering patterns, ensuring data quality and guiding further analysis.

NLP

NLP

Natural Language Processing (NLP) is used to analyze and understand human language data, crucial for applications like sentiment analysis and chatbots.

Machine Learning

Machine Learning

Machine learning is used to build predictive models and algorithms, enabling data-driven decision making in various industries.

Deep Learning

Deep Learning

Deep learning is used for advanced machine learning tasks like image and speech recognition, leveraging neural networks.

Big Data

Big Data

Big Data technologies like Hadoop and Spark are used for processing large datasets, providing scalability and efficiency.

Data Visualization

Data Visualization

Data visualization tools like Power BI and Tableau are used to create interactive dashboards, making data insights accessible and understandable.

Cloud Computing

Cloud Computing

Cloud platforms like AWS and Azure are used for deploying and scaling applications, offering flexibility and cost-effectiveness.

Research Skills

Research Skills

Research skills are essential for conducting experiments, analyzing results, and advancing knowledge in various domains.

Experience

Data Science Icon

Data Scientist, Infosys

  • Utilized clustering algorithms (K-means, DBSCAN) and principal component analysis (PCA) to segment customers, leading to targeted marketing strategies and a 20% increase in customer engagement.
  • Involved in development and fine-tuning ARIMA, Prophet, and LSTM models for sales forecasting, resulting in a 20% improvement in forecast accuracy.
  • Developed predictive models that reduced patient readmission rates by 20%, enabling early identification of high-risk patients and personalized interventions.
  • Designed and conducted A/B tests to evaluate the impact of new features and marketing strategies, providing data-driven recommendations that increased conversion rates by 10%.
  • Conducted performance tuning and optimization of Power BI reports, reducing load times by 20% and improving user experience.
  • Involved in the development and documentation of a generative AI chatbot using transformer-based models like GPT-3, significantly enhancing customer satisfaction by 15% and reducing the support workload through automated, intelligent responses in a high-impact client project.
  • Enhanced the accuracy of sentiment analysis from 88% to 95% using cutting-edge natural language processing (NLP) and transformer models in a global employee feedback analysis initiative, leading to substantial cost savings.
BI Engineer Icon

Data Science and BI Engineer, Infosys

  • Created predictive models using ensemble learning techniques (Random Forest, Gradient Boosting) in healthcare projects, achieving a 20% reduction in patient readmission rates by identifying high-risk patients early.
  • Conducted complex data analysis and visualization using Python (pandas, scikit-learn, matplotlib) and R (ggplot2, caret), providing actionable insights to business leaders.
  • Led data modeling and SQL optimization projects, enhancing data quality by 25% in several enterprise-level systems.
  • Developed DAX measures and enforced row-level security, enhancing report performance and reliability.
  • Streamlined ETL processes integrating data from multiple sources, enhancing efficiency by 12%.
  • Engineered multi-dimensional data models and OLAP cubes for enterprise business intelligence solutions, optimizing schema design and enhancing user experience by 15% in executive dashboards.

Projects

Team Lead
US Presidential Election Sentiment Analysis

US Presidential Election Sentiment Analysis

This project analyzed public sentiment on Twitter to predict the winning candidate in the 2020 US Presidential Election using machine learning techniques. It involved extensive data analysis, feature engineering, and the implementation of various machine learning models including Random Forest, Decision Trees, and NLP techniques. Such a project demonstrates the power of social media analytics in understanding and forecasting political trends, which can be invaluable for political campaigns and market research firms.

Technologies: Python, NLP, Twitter API

#SentimentAnalysis#NLP#TwitterAPI
Team Player
Predictive Analysis for Crime Hotspots

Predictive Analysis for Crime Hotspots

Leveraged predictive modeling to identify high-risk areas for crimes against women in India, assisting law enforcement in resource allocation. This project utilized data analysis and machine learning techniques to uncover patterns and insights from complex datasets. The implementation of such predictive models can significantly enhance public safety measures and optimize the deployment of law enforcement resources.

Technologies: Python, Scikit-learn, Pandas

#MachineLearning#DataAnalysis#Python
Lead Engineer
Customer Segmentation

Customer Segmentation

Performed customer segmentation using clustering algorithms to help businesses tailor their marketing strategies and improve customer engagement. Techniques like K-Means clustering and data visualization were employed to identify distinct customer groups. Businesses can leverage such insights to create targeted marketing campaigns, enhance customer retention, and optimize product offerings.

Technologies: Python, Scikit-learn, K-Means

#Clustering#CustomerSegmentation#Python
Team Player
Artifacts Detection using CNN

Artifacts Detection using CNN

Implemented Convolutional Neural Networks (CNN) to detect artifacts in images, showcasing deep learning techniques in image processing and quality control. This project involved the use of TensorFlow and OpenCV for building and training the neural network models. Such applications are critical in industries like manufacturing, healthcare, and automotive, where image analysis and quality control are paramount.

Technologies: Python, TensorFlow, OpenCV

#DeepLearning#CNN#ImageProcessing
Personal
Applicant Tracking System using LangChain

Applicant Tracking System using LangChain

Developed an Applicant Tracking System (ATS) to enhance resume content and streamline the job application process using natural language processing techniques. This project demonstrates the integration of NLP models and automation to improve HR processes, making it easier for companies to identify top talent and manage large volumes of job applications efficiently.

Technologies: Python, LangChain, NLP

#NLP#Automation#ATS

Contact

Email: lohithprasannateja@gmail.com

Phone: +17169077542

LinkedIn Profile

This website is solely created by Lohith Prasanna Teja Kakumanu and chatgpt is used for optimizing. Published under University at Buffalo, The State University of New York (buffalo.edu).