Dengue affects thousands of lives each year and continues to be a major public health problem in the Philippines. In the last year alone, the Philippines experienced the worst dengue outbreak since 2012 as reported cases reached beyond epidemic thresholds. On top of that, the delayed reporting of official case and death counts makes it even more difficult to pinpoint heavily dengue affected areas early on and initiate a targeted public health response.

Pinoy dengue case predictor, Project Aedes, won the 2019 NASA International Space Apps Challenge in the best use of data. Keen to use this information operationally, Janine Padilla, Mox Ballo, and Rache Melendres, developed a publicly accessible web application that can be used by concerned government agencies and public health officials to predict the spread of dengue and visualize potential breeding sites of mosquitoes.

We may be nowhere near eradicating Dengue, but we may be able to prevent it more effectively. Through Time-Series Modeling and geospatial mapping, Team Flex was able to predict and forecast cases and deaths up to 4 months and identify potential dengue hotspots in selected cities of the CALABARZON region.

The Bangsamoro Autonomous Region of Muslim Mindanao (BARMM) has been hit by 232 earthquakes in the past 50 years, including the 3 consecutive earthquakes that rocked Cotabato City in October 2019. To help the BARMM government become more resilient, Team Spyce Girls composed of Elaine Cotoner, Kimberly Cris Estrella and Sarah Khey Ebido deployed a hazard map that indicates low, medium, and high-risk municipalities based on magnitude, depth, and how often earthquakes occur in the area.

Using data from the SHP file from Open Bangsamoro and earthquake data set from USGS, the team focused on making a specific earthquake hazard map to give a clearer picture of where the hazard areas are. This information will help in earthquake preparedness, disaster management program, and urban planning of BARMM.

Today, electricity has become one of our basic needs. As consumers, it has become quite impossible to be independent of it to the point that it has been taken for granted. Behind the ease of flicking a switch to turn on the lights is a convoluted market for electricity. Just like any other good, electricity is trade-able and its trading is as complicated as it gets.

To help AC Energy understand the market better, generation and bidding profiling of gencos was conducted by Alyssa Katelyn Castillo. By identifying the activities and tendencies of each plant, more informed actions in the market are made available. Add to that being able to assess the bidding behavior of competitors, a competitive advantage is created.

These days, electricity has become a basic good, but it is rarely understood. It's a little known fact that there is a market for electricity. Even more so, that electricity in the Philippines is a tradable commodity. Knowing how this market works and what power plants actually do is both informative and interesting to know.

About less than 5% of Filipinos invest in the Philippine Stock Exchange. It can be daunting to learn how, when and if to trade at all. Team MCU members Isabel Mañalac, Alexis Canaria and Erika Ureta took on the challenge of helping more Filipinos get into trading and increase their financial literacy. But by being part of the 95%, themselves, the team first learned how traders think, and that the market moves with their sentiment. Using Twitter as one medium for reading the market, tweets and stock quotes from 2012 to 2020 were scraped and modeled together to analyze movement affecting factors.

Trading is a field that needs to be explored more by every Filipino as only around 5% are actually diving deep into this field. With their study, the team showed that tweets can be an indicator of PSEi stock market movement - which makes it possible to deduce stock market movement from human actions.

Charlene Grajales, Dina Derla and Maria Regina Corazon Sibal of Team IntensiPy took on the challenge of identifying sales drivers from an appliance distributing and sales company. The challenge was to look into a year’s data with 347 thousand sales records and 14 features, as they tried to solve, “What are the sales drivers for an appliance? How do these drivers affect sales?”

Weekly company sales data as well as client validate competitor data was explored for data visualization, analytics and model development. The team was able to produce an interactive dashboard highlighting major sales drivers for the company, share key insights and observations from the data and looked into possible external factors that can validate the results. They went further to create a prototype sales predictor web application that can generate weekly projections for sales for user selected features.

The study was was helpful to the company and its template can also be used for other sales and marketing companies as the study resulted in the following:

-Interactive Dashboard shows how relevant sales data can be visualized

-Analysis and observations helped identify trends and key insights on sales

-Web application predictor prototype can help predict sales using different features

Julia Krista Villadiego, Charina Brickly Ortiz, Marj Pabilonia and Franchesca Ivane Manuntag of Team OMQ was initially tasked to create a Headline Analyzer for a Content Marketing Agency to capture the attention of their niche market. But is headline enough? There is a shift in the viewership and the client needs to identify what exactly do their target readers want. Using advanced data science techniques such as LDA (Latent Dirichlet Allocation) Topic Modeling and XGBoost Regression, the team took on the challenge of creating ART-E (ARTicle Evaluator), a tool that can describe what exactly makes an article popular and predict viewership even before an article gets published.

With this, an editorial team can plan their content based on what their niche market really prefer instead of relying on their intuition as to what topics they can write about. The techniques used in this project can be applied to other fields and industries as well (e.g. identifying latent topics in research/legal docs).