Predictive Analytics Solutions: Off-the-shelf or Custom?
October 2nd, 2024
In-depth Analysis – about the results
Due to the government’s request to the Estonian population to stay more at home during the emergency, MindTitan, together with our partner Elisa, analyzed the extent to which the call has been complied with. The analysis showed that 72% of people stayed at home for a significant amount of time.
Today, the emergency in Estonia has lasted for more than three weeks and the Government of the Republic of Estonia continues to ask people to stay at home and move around as little as possible. To find out how many people have followed this call, together with Elisa, we analyzed their anonymous network data.
According to Mailiis Ploomann, Head of Elisa’s Telecommunications Services, the analysis showed that if Estonia is considered as a whole, a little over half (56%) of the population stayed at home most of the time before the state of emergency, and immediately after the state of emergency it increased to 72%.
“The biggest change was probably caused by the closure of schools and the massive reorientation to remote working, as the number of people who spent fewer than 17 hours at home so far decreased, while the number of people who spent more than 90% of the day at home increased,” Ploomann said about the study.
“Our common desire is to leave this emergency as soon as possible and for this, it is important to stay at home in the coming weeks,” said Ploomann.
To make the research visually observable, Elisa also published the results on their website and will update the data daily until the end of the emergency.
Results can be found here: www.elisa.ee/kratid
For easier interpretation of the data, all people are divided into five categories:
- People staying at home for up to a third of the day (for example, only at night)
- People who stay at home up to 70% of the day (for example, they go to work, but stay at home for the rest of the time)
- People who stay at home up to 90% of the day (away from home for 2-4 hours a day)
- People who stay at home more than 90% of the time (just over 2 hours away from home)
- Also, those who stay at home (or close to home) 100% of the time are shown separately.
How is the analysis done?
In the results, the word “home” and “time spent at home” are used. It is important to point out that this is a computational location where different data points are most often located at night. “Whether it’s home or not, we don’t know,” explains MindTitan CEO Kristjan Jansons. “Based on this point, we compare how much of the day was spent in the same location or elsewhere.”
Analyzing anonymous traffic data is common for mobile companies. “Only in this way can we ensure the performance of the network and the availability of vital services exactly where people want and need to use it. “Based on this, we also plan, for example, volume and coverage extensions in our network and measure the user experience,” said Ploomann. However, on this occasion, data researchers needed to work on their models for a slightly different purpose to assess changes in mobility.
“It is an honor for us as data scientists to contribute with this analysis to the common fight against the oppressive health crisis. We hope that our previous years of experience working with mobile data has become an application in a completely new and hopefully beneficial way for all of us,” added Jansons.
MindTitan as an AI company and Elisa, as a responsible operator, call on everyone to take the Government’s call seriously, and we hope to see a growing trend in terms of staying at home. This means that we would have as many people as possible who leave home, for example, for an hour or two to get fresh air or who go to shops for brief shopping, but most of the time they stay at home.
Want to learn more?
Want to learn more?
Kristjan Jansons
Co-founder, CEO
Kristjan has been studying and working on machine learning projects for more than 7 years.
After acquiring a Master’s Degree in Computer Science and Machine Learning, he started working at Milrem Robotics as the Team Lead for Autonomous Vehicles, helping to build self-driving vehicles.
Kristjan also has experience in building intelligent systems for data centers, robots and electric formulas; also with computer vision and image recognition. He is especially fascinated by how people from different industries combine their knowledge with data science, arrive at new insights and help to accelerate innovation.
Want to learn more?
Want to learn more?
