Cécile Wendling also led a roundtable on governance tools for responsible AI during the conference organized by Impact AI on AXA's Java site on January 25, 2019. Artificial intelligence will impact insurance in several ways. First of all, it can help change the way insurance companies interact with customers and improve the customer experience. Take the example of damage occurring overnight during a major disaster. At a time when a traditional call center may be closed or busy, we can now imagine customers contacting a chat bot or voice bot to get instructions on the first steps to take in case of damage.

AXA has deployed three new AI (artificial intelligence) bots to support staff across the business with repetitive admin work. Named Harry, Bert and Lenny – the insurer has projected that the bots will save 18,000-man hours per year. And the three bots will soon be joined by a fourth – Como who will work on the commercial motor team. Throughout this year they will be expected to pick up more admin tasks, allowing staff to turn their attention to more analytical tasks. It follows the roll-out of Harry in June 2018.

The global insurance industry will grow more strongly than the global economy in 2018 and 2019, Munich Re predicts in its latest outlook. "This year and next, we expect global premium to grow by more than €460 billion in all. This is equivalent to average annual premium growth of 5.3% (in real terms, i.e., adjusted for inflation: 3.7%), whereas global GDP is expected to grow by only 4.9% (3.3% in real terms). Life insurance, in particular, looks set to return to strong annual premium growth of 5.6% (3.9% in real terms) after a weak 2017. Property-casualty insurance is benefiting from the currently favorable economic environment. In this segment, we are expecting annual growth rates of close to 5% (3.3% in real terms). Emerging countries are the primary growth drivers, but somewhat stronger growth rates in high-volume industrialized countries are also contributing to this positive development."

A shortage of charging points and strain on energy supplies are now the main stumbling blocks to the rise of driverless electric cars, according to the UK boss of insurer Axa. Amanda Blanc said a lack of rapid charging bays and pressure on the National Grid have overtaken questions about accident liability as the biggest barriers to autonomous vehicles entering the transport mainstream. Blanc, a Tesla driver, said personal experience pointed to problems lying ahead for driverless electric vehicles. There are around 125,000 plug-in electric cars in the UK and 14,000 chargers - 2,620 of them being rapid chargers that can give a car an 80% charge in 30 minutes. Shell has just opened its first charging points for electric vehicles at 10 filling stations, mostly in London and the south-east.

AXA, the large global insurance company, has used machine learning in a POC to optimize pricing by predicting "large-loss" traffic accidents with 78% accuracy. The TensorFlow machine-learning framework has been open source since just 2015, but in that relatively short time, its ecosystem has exploded in size, with more than 8,000 open source projects using its libraries to date. This increasing interest is also reflected by its growing role in all kinds of image-processing applications (with examples including skin cancer detection, diagnosis of diabetic eye disease and even sorting cucumbers), as well as natural-language processing ones such as language translation. We're also starting to see TensorFlow used to improve predictive data analytics for mainstream business use cases, such as price optimization. For example, in this post, I'll describe why AXA, a large, global insurance company, built a POC using TensorFlow as a managed service on Google Cloud Machine Learning Engine for predicting "large-loss" car accidents involving its clients.

In Property and Casualty Insurance, information is the currency that drives pricing, claim loss prediction and prevention, risk management and customer experience. AXA, a global insurance company, created a proof of concept (POC) using machine learning to optimize pricing by predicting "large-loss" traffic accidents with 78% accuracy. Profitability in the insurance industry comes from two streams; the ability to identify high risks and then price them appropriately. Each year approximately 10% of AXA customers experience a loss. While the cost of most losses are in the hundreds or thousands of dollar range, about 1% are considered large losses; in excess of $10,000.

AXA, the large global insurance company, has used machine learning in a POC to optimize pricing by predicting "large-loss" traffic accidents with 78% accuracy. The TensorFlow machine-learning framework has been open source since just 2015, but in that relatively short time, its ecosystem has exploded in size, with more than 8,000 open source projects using its libraries to date. This increasing interest is also reflected by its growing role in all kinds of image-processing applications (with examples including skin cancer detection, diagnosis of diabetic eye disease and even sorting cucumbers), as well as natural-language processing ones such as language translation. We're also starting to see TensorFlow used to improve predictive data analytics for mainstream business use cases, such as price optimization. For example, in this post, I'll describe why AXA, a large, global insurance company, built a POC using TensorFlow as a managed service on Google Cloud Machine Learning Engine for predicting "large-loss" car accidents involving its clients.

Behavioural change is a very tricky thing. We humans are so fickle. We see a bright shiny wearable device that can track our every move and we think it's our "silver bullet", a "ticket" to achieving our health and fitness dreams. Only for guilt to set in, as after a short time, the wearable device winds up in our top drawer. We knew the fitness data was great, but we really didn't know what to do with it. The truth is, behaviour change requires much more than data.

Behavioural change is a very tricky thing. We humans are so fickle. We see a bright shiny wearable device that can track our every move and we think it's our "silver bullet", a "ticket" to achieving our health and fitness dreams. Only for guilt to set in, as after a short time, the wearable device winds up in our top drawer. We knew the fitness data was great, but we really didn't know what to do with it. The truth is, behaviour change requires much more than data. Many programs have realized the magnitude of the problem and created incentive programs to reward people for being active, so they get a small pay-off on the road to achieving fitness. But in spite of these rewards, the drop-out rate remains problematic.