Tag Archives: big data

Riding the data: How a transportation company used data science to improve decision-making processes

How can a company leverage customer data and turn it into actionable information? This was the challenge one transportation provider faced when its modeling system began underperforming after the company implemented it to predict revenue and passenger traffic. In this article, Milliman consultant Antoine Ly discusses how the firm created a machine-learning model that helps the company analyze various aspects of its ridership, leading to more informed financial decisions.

Here is an excerpt:

Working from a mock-up drafted by the client, the [Milliman] team reproduced the dashboard to the client’s specifications, but it is now supported by newly developed software as well as the client’s data warehouse. The dashboard allows the client’s management team to quire different aspects of passenger usage to gain insight into traffic flows and revenue. Colour-coded symbols, which when clicked on, give managers a concise picture of a train’s revenue and traffic. Managers can also quire the system based on selected features for both past usage and anticipated ridership, and are now able to make more informed decisions about pricing, the need for discounts or adjustments to marketing campaigns.

Because the model can adapt to new situations, deviations from the average error are confined to a much more narrow range. This means managers can have more confidence in the model’s predictive value and increases their ability to manage revenue.

The Data Science Game is back

Registration for the 2017 Data Science Game is officially open. The Data Science Game is a two-phase competition showcasing teams of data science students from universities around the world. An online qualifier will take place on April 15 with the final stage happening in September.

Students from the Moscow Institute of Physics and Technology (MIPT) won last year’s competition. Will your university win this year? To register your team, visit www.datasciencegame.com. The deadline to register is April 9.

Milliman is a sponsor of the 2017 Data Science Game.

Big data challenging how insurers think about business

The insurance industry has a long history of using data to make decisions around risk. However, as more and more data on risk becomes available, insurers will encounter numerous business challenges. In the Milliman Impact article “Harnessing the transformative power of big data,” consultants Neil Cantle, James Dodge, and Derek Newton offer perspective on big data and its implications for insurers’ business models, data governance, and skills moving forward.

Big data, consumers, and the FCA

Newton_DerekIn November 2015 the Financial Conduct Authority (FCA),1 a UK financial services regulator, announced that it intended to investigate the use of “big data”2 in retail general insurance in the UK. In September 2016, it announced that it was not, after all, going to pursue this investigation. Why this apparent turnaround?

The opportunities big data provides general insurers are widely acknowledged and the reason general insurers are investing heavily in this area. But with such opportunities come potential threats: big data could potentially lead to better service and outcomes for many consumers, but could it also lead to some consumers effectively being excluded from the market, or to the exploitation of consumers who are less price-sensitive than others? They are the concerns that the FCA sought to address when announcing its investigation in November 2015.

Since then, the FCA has been gathering and evaluating relevant information, mostly relating to private motor and home insurance. It has found a lot of evidence that the use of big data results in benefits to users of insurance, through products and services being better tailored for individual needs, through more focused marketing and better customer service, and through increasing feedback to consumers about the risks that they run and how to manage them effectively, most notably to those with telematics auto insurance.

While its concerns remain, the FCA concluded from this preliminary investigation that the increasing use of big data is “broadly having a positive impact on consumer outcomes, by transforming how consumers deal with retail GI firms, streamlining processes and encouraging more innovation in products and services.” As a result, it has decided that there is no immediate need either to push ahead with the full investigation that it had originally proposed or to change its regulatory framework in response to any issues raised. However, it will continue to look at big data, in particular looking for any related data protection risks and seeking to understand how big data is used in pricing.

Full details of the FCA’s views can be found in its Feedback Statement FS16/5.


1The FCA regulates the financial conduct of the financial services market within the UK and shares with the Prudential Regulation Authority the prudential regulation of the businesses within the UK financial services market.
2There is no universally accepted definition of “big data.” In the context of its investigation, the FCA considered big data very broadly, embracing data sets that are larger or more complex than have hitherto typically been used by the insurance industry, data sets derived from new sources such as social media, and the emerging technologies and techniques that are increasingly being adopted to generate, collect, and store the data sets, and then to process and analyse them.

The 2016 Data Science Game winner is…

Russian Data Mafia from the Moscow Institute of Physics and Technology (MIPT) won the 2016 Data Science Game. The final phase of the game featured teams of students from 20 universities competing in a 30-hour hackathon challenge.

DSC_0347 (2)

Microsoft provided its support by giving free access to its Azure computing clusters while the final challenge was set by AXA. Each team worked on a data set containing requests for auto insurance quotes from different brokers and comparison websites. Students were asked to predict whether the person who requested a given quote bought the associated insurance policy. Teams were ranked according to their prediction scores.

The final phase took place September 10 and 11 at Capgemini’s Les Fontaines campus in France. This year, 143 teams participated from more than 50 universities and schools in 28 different countries.

To learn more about the Data Science Game, click here.

The Data Science Game’s qualification round is complete

In July, teams of data science students from more than 50 universities around the globe competed in the qualification phase of the 2016 Data Science Game. Over 140 teams of four students were asked to develop an algorithm that could recognize the orientation of a roof from a satellite photograph by building on more than 10,000 photograph of roofs categorized through crowdsourcing.

Twenty-two teams have qualified for the final phase. The top three ranking teams were Jonquille (University Pierre and Marie Curie), PolytechNique (Ecole Polytechnique), and The Nerd Herd (University of Amsterdam). The final is being held in Paris on September 10 and 11, where the teams will compete in a big data analysis challenge.

Data Science Game finalists

For more information on the Data Science Game, click here.

Milliman is a sponsor of the 2016 Data Science Game.