NEWYORK-An IBM master inventor has harnessed the power of social media activity to develop a system that predicts recurrent 'crowd mobility' in metropolitan areas.

Called Temporal Functional Regions, this technology uses machine learning to gather mountains of data in order to predict where people are most likely to be at certain times during the day.

Using New York City's five boroughs as a pilot study, Haytham Assem has developed maps that highlight distinctive patterns of activities and also identifies areas of concern.

Click the arrows beneath the clock to see what New Yorkers are doing at different points of the day.

Temporal Functional Regions uses machine learning to gather mountains of data in order to predict where people are mostly likely to be at certain times during the day.Using New York City's five boroughs as a pilot study, Haytham Assem has developed maps that highlight distinctive patterns of activities and also identifies areas of concern within the five boroughs.

Temporal Functional Regions, this technology uses machine learning to gather mountains of data in order to predict where people are mostly likely to be at certain times during the day.

The information presented in the map is results of what people are actually doing in an area. Businesses can use this information – a restaurant owner could take a look at the model and in just a few seconds see what areas have the most foot traffic and during what times.

Haytham Assem, the creator of this machine learning system, is able to see when people first log on to their favorite social media site in the morning, what they are doing throughout the day and when the sign offline at night.

Other than online trends, the maps allow officials to see if there are areas of concern.

If people are heavily tweeting during work hours or getting up later may suggested the neighborhood has a higher level of unemployment.

'Most of the work I do is related to smart cities and anything that can better impact how they operate,' Assem told DailyMail.com.

'I am constantly asking myself how we can drive analytics to make our cities better, which is what has inspired me to do what I am doing'.

Location-based social networks have allowed people to check out the best hotspots in an area, based on where their friends have visited.

However, Assem believes the system failed in providing 'the shifting temperature of a vibrant city'.

'Every region in the city has a dynamic functionality through time, and for the first time, we can show this,' he explained in a statement.

'In the morning it might be education, then in the evening it might be an area rich in restaurants and nightlife. This is a new level of granularity we've achieved in the big data era.'

'We are able to build cognitive models that show the way regions change in relation to time of day.'

'The impact of this will be the ability of marketers to make highly personalized recommendations, based on these temporal functional regions.'

Now with Assem's machine learning-based system, which he refers to as Temporal Functional Regions, you can see the patterns of movement – such as where people eat during lunch or popular spots to enjoy nightlife.

And this is not based on an acquaintance's check-in – it is exactly what people are doing.

Using this technology in New York City has also let Assem predict where patterns are happening.

The pilot study with New York City was develop using data from Twitter, Foursquare and other popular applications.

While analyzing the data, Assem is able to see when people first log on to their favorite social media site in the morning, what they are doing throughout the day and when the sign offline at night.

'We use Insights for Twitter on Bluemix—the default stream is 10 percent of overall Twitter use,' he said. 'The impact of this is that you will extract a different pattern in Brooklyn than you will in Manhattan.'