UBS trials artificial intelligence wealth managers

Tools can read facial expressions and uncover clients' unconscious biases

Wealth management firm and investment bank UBS is running artificial intelligence (AI) trials with some of its richest clients.

AI applications being tested include tools designed to read facial expressions and uncover clients' unconscious biases towards or against certain types of investment.

The aim is to help the company's cash-rich, but time-poor, clientele to ask the right questions about their decisions, according to UBS.

The move comes as little surprise. The financial services market is in the vanguard of automation, AI, machine learning and robotics at a time when many customers prefer app-based mobile banking to online or bricks-and-mortar alternatives.

Several international banks plan mass software automation, including HSBC and Bank of America investment arm Merrill Edge.

RBS announced earlier this year that the bank may replace hundreds of face-to-face customer service staff with automated services, which it claimed will free its remaining human agents to be expert advisers.

These advisers will be available only to RBS' wealthiest clients, effectively making face-to-face human service a luxury for those who can afford it.

In this context the UBS move is unusual: an application designed to maximise the financial return from, and to, its richest customers, rather than to cut the cost of service provision to its poorest ones (the standard application of automation).

Fraud detection is another area ripe for AI applications, and companies such as Ravelin have deployed machine learning capabilities to identify online payment fraud and other pattern-based behaviour.

Automation, AI and robotics are spreading fast into other sectors too, not least marketing and CRM with the much-trailed launch of Salesforce.com's Einstein AI product at its Dreamforce event next month.

AI applications are also being used by local authorities, such as Oxfordshire County Council, in environmental planning and traffic management programmes.

In the related field of hard and soft robotics, Royal Dutch Shell announced today that it is trialling a semi-autonomous safety monitoring 'Sensabot' at a facility in Kazakhstan, the first such robot to be approved in the oil and energy sector.

IBM and Aldebaran Robotics (now majority owned by Japan's SoftBank) have been testing a robotic concierge service using IBM's Watson service in the cloud via industry-specific datasets provided by 'cognitive travel agent' WayBlazer.

It stands to reason that sector-specific big data services of this type will become a major growth market over the next five to 10 years, as the enterprise applications of AI and automation spread.

Meanwhile, Bloomberg and Associated Press are pursuing automation in the production of journalism and other editorial products and services, based on press releases and trending topics.

UK government-backed startup PingGo announced last week that its mission is to automate PR, giving rise to the real possibility that press releases may soon be produced by robots for other robots to read and disseminate as machine-readable news.

More and more jobs now rely on repetitive behaviour, schedules, timesheets, regulations and software, and many human roles are already little more than algorithms.

Dr Anders Sandberg, James Martin Research Fellow at Oxford University's Future of Humanity Institute, observed earlier this year that if you can describe your job it can and will be automated.