Crystal Mejia

About

I'm a Columbia University graduate with a Bachelor of Science in Biomedical Engineering. In the past, I've worked in the pharmaceutical marketing industry on drug launches and product rebranding.

Recently, I completed the Correlation One – Data Science for All program, which has allowed me to build up my skills in programming, data analysis, and data visualization. I’m excited to start leveraging these new skills. I want to use data analytics to develop strategic insights and contribute to the growth and transformation of businesses.

Are you interested in seeing some of my work? Check out my projects page.

Projects

Morning Brew Accelerator - Business Case Studies

Branding | Leadership | Business and Financial Analysis | Innovation | Strategy

Through a series of modern case studies, research approaches were applied to generate business recommendations and refine strategy, problem-solving, and collaboration skills. In the Under Armour case study, an examination of nurturing internal culture versus rebranding advocated for prioritizing internal restructuring alongside recommendations for leadership and management improvements. An analysis of investment prospects highlighted Cann Social Tonics' strong market position and exceptional individual performance. Similarly, the case study of Spotify led to the ideation of innovative concert and travel ventures, providing strategic insights for industry growth and differentiation.

Using Classification Model to Identify Features Associated with Song Popularity

Python | Spotipy | Billboard | Numpy | Pandas | Matplotlib | Seaborn | Tableau | Scikit_learn | Git

Music streaming platforms, such as Spotify, have allowed the music industry to move to digital and have changed the market prioritization. In this new music ecosystem, artists and labels are challenged to determine how to best invest their time, energy, and resources to create music that will reach a broad audience. This project explores patterns and features in popular music in recent years and aims to use data science techniques to better understand the makings of a popular song. A logistic regression classification model was created to measure the predictive power of audio features on determining if a song is a hit or not. Feel free to read through the full report.

Diagnosing Bacterial Ear Infections with a Machine Learning Algorithm

SOLIDWORKS | 3-D Printing | MATLAB | Python | TensorFlow | Support Vector Machine

Acute otitis media (AOM), or ear infection, is the most common childhood infection. The use of an otoscope is the primary but inaccurate method for the diagnosis of bacterial AOM. It is estimated that 50% of antibiotic prescriptions for ear infections are unnecessary and potentially lead to a weaker immune system, expose the child to subsequent episodes of AOM, and further increase the likelihood of antibiotic resistance. AURI is a rapid and painless device that accurately diagnoses bacterial ear infections by analyzing eardrum bulging. Using a support vector machine (SVM) classification and Google's TensorFlow, the device is able to capture an image of the eardrum and extract features to produce a classification result. You can dive deeper by reading through the full report.

Check out my GitHub for some of my additonal coding projects.

Contact

If you want to connect, feel free to message me on LinkedIn.

• LinkedIn




Also, you can find some of my additonal coding projects on GitHub.

• GitHub

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';