About me & ContactA few interesting things about me. I love to play Action Adventure games(Sekiro) and first-person shooters(Valorant, Apex). On top of I am a Master's student in School of Computing from Clemson University, I also recently started working as a Graduate Research Assitant at Clemson University. My work mainly revolves around building Machine Learning Models and Data analysis.
As a student aspiring to launch my career in the field of data analysis and data science, I am eager to contribute to projects, internships, or research opportunities that allow me to apply my skills and learn from experienced professionals. I am open to collaborations and eager to engage in discussions on emerging trends and technologies in the industry.
I love telling a story. Getting to the heart of a problem and coming up with a solution.
I am passionate about learning the theory that is pushing the cutting edge of ML.
I apply text analytics to some of the hardest questions in business.
I enjoy working with my team to create winning strategies.
I utilize AWS to develop and productionize machine learning systems.
Take a look at my recent work.
A Guide to Training, Monitoring, and Deploying Machine Learning Models in AWS" is a tutorial on using Amazon SageMaker to manage the machine learning lifecycle. It guides users from setting up an AWS account to deploying models, covering data preparation, model training, hyperparameter tuning, and deployment. The article also explains how to integrate models into applications using Lambda functions and API gateways, making it a practical resource for developers and data scientists using cloud computing for machine learning projects.
This project leverages the LLaMA pre-trained language model to boost summarization accuracy through fine-tuning with customer and agent conversation data, achieving a 15% improvement in accuracy. The focused approach on custom data fine-tuning demonstrates the process's effectiveness and sets new accuracy standards in automated conversation summarization. It highlights the potential for further advancements in natural language processing by using refined methodologies.
This project enhances sales forecasting with a new model that blends machine learning techniques like LSTM, 1D CNN, and GRU, achieving a 15% increase in accuracy through hyperparameter tuning and optimization. This advancement sets a higher standard for precision in forecasting, demonstrating the effectiveness of combining different algorithms and offering insights for strategic decision-making.
This project presents a solution to the challenging task of evaluating the quality of skull stripped brain MRI images. In the field of neuroimaging research, such images are frequently shared in open access data repositories. However, ensuring the accuracy and reliability of the segmentation results is a time-consuming process. To address this issue, the authors propose a deep neural network algorithm based on 3D Convolutional Neural Networks (CNN). By leveraging the power of CNNs and their ability to analyze 3D medical data, the algorithm automates the inspection of skull stripped MRI images and aims to improve the overall accuracy of the segmentation process.
This project aimed to develop effective models for fine-grained aspect-based analysis of product reviews in natural language processing. Data cleaning steps were performed, and exploratory data analysis was conducted. Three models were implemented: 1D CNN, RNN/LSTM, and BERT. However, the models did not perform as well as expected, with accuracy scores below the desired level. Despite the limitations, valuable insights were gained, emphasizing the challenges in fine-grained aspect-based analysis.
Explore our Tableau-based Sales Data Dashboard for WeWashUSleep, a startup focused on expanding its network in smaller cities. This interactive dashboard offers insights into regional sales performance, revenue comparisons between established and new cities, and aids investment decisions based on population and marketing spending. Uncover trends, make informed decisions, and drive growth with actionable data insights.
