Embarking on a journey into the realm of data, where empowering decision-making is the key to unlocking insights for resounding success.
Engineering | Cloud | Data | All Outdoor Activity
I am a passionate and dedicated learner, constantly seeking out new challenges and embracing the opportunity to acquire new knowledge. I have recently expanded my professional skill set, honing my expertise in Python, Django, Flask, Javascript, React JS, Express JS, R, SQL, and various other tools vital to data analysis and visualization. Building upon my foundation in statistics and my previous studies in software engineering and self studies in Data Architectures. I am currently pursuing a Masters Degree from Auckland University of Technology in Computer and Information Systems, prioritizing research in Data Warehouse, Big Data and Software Engineering. I am open to part-time or internship positions while I complete my masters in the realm of data. Relevant disciplines would include Data Engineer, Backend Engineer, Machine Learning Engineer, Cloud Solutions and/or Data Scientist.
I thoroughly enjoy challenges and my appetite for them extends far beyond the realm of business and data. From learning to surfing to summiting mountains, the exhilaration derived from tackling and ultimately triumphing over these endeavors is a lasting source of inspiration.
Landslides can cause significant damage to property and loss of life, making their prediction an important area of research. This dataset provides information on various geological and environmental factors that can contribute to the occurrence of landslides. By training a machine learning model on this dataset, we can develop a tool that can predict the likelihood of a landslide occurring in a given location, based on the features provided. Such a tool could be used by governments, emergency responders, and other stakeholders to better prepare for and mitigate the impact of landslides, potentially saving lives and reducing the economic impact of these events.
This notebook uses geospatial feature engineering to predict the prices of Airbnb listings in New Zealand, leveraging data from Yelp!, Open Street Maps, and geographically weighted spatial lags. The notebook creates predictive models, including linear regression and geographically weighted regression, and evaluates them using various metrics. The analysis attempts to provide insights into the factors influencing Airbnb pricing in New Zealand and demonstrates the potential of geospatial analysis for predicting real estate prices.
For this dataset, we will be performing an RFM analysis on customer transaction data. RFM stands for Recency, Frequency, and Monetary Value, and is a widely used customer segmentation technique that helps businesses better understand their customer base. By analyzing customers based on their recency of purchase, frequency of purchase, and total monetary value spent, businesses can gain valuable insights into which customers are most valuable, which customers are at risk of leaving, and which customers require additional attention or marketing efforts. Ultimately, an RFM analysis can help businesses improve customer retention, increase revenue, and optimize marketing strategies.
A market basket analysis is effective for identifying customer behaviors. It uses a technique called associated rule learning for Data Mining. It involves analyzing transactional data to identify the relationships between products that are frequently purchased together. By analyzing these associating we can recommend store layout plans to optimizing purchasing items or to cross sell and upsell products based on what is being purchased!
For my two week capstone project, I demonstrated my new skills by collecting satellite imagery and creating a deep learning model to classify satellite imagery into specific land use categories. Semantic segmentation is a technique used in remote sensing and computer vision to classify each pixel in an image into different classes or categories. The application of semantic segmentation using Landsat imagery is important due to the widespread use of Landsat data for environmental and resource management.