Intelligence analyst with 3 years of experience in analyzing data and assessing risks. Dedicated to collaborating across departments to create detailed intelligence reports. Skilled at putting together intelligence products, maintaining records and briefing leadership. Strong capability to adapt to new software and processes.
1st place at the Interstate 'Science and Engineering Fair
The study included the evaluation of sentiments from tweets during the Super Bowl, the Oscars and the Grammy’s using Word cloud and In Document Term Frequency (Tf-IDF ) analysis to identify key influencers and profitable ads necessary to increase business productivity. Network graph analysis was performed using Gephi.
The study included the use of machine learning models, namely Naive Bayes, Classification Tree, K-Nearest Neighbour, Neural Network and Logistic Regression to predict employee attrition patterns. Logistic Regression model provided the best sensitivity, accuracy and misclassification results.
The study included the use of forecasting models such as seasonal naïve, linear regression, Holt - Winters and TBATs to predict tourists visiting Thailand. Results showed that the Holt-Winters model was the best fit model for predictive analysis