We are not just one person. One of the challenges of personalisation is that each of us
combines many moods, modes and contexts in a single human being. My mood differs from
one day to the next as I move from relaxed to busy. My mode moves from work to
parenting to sports fan to film buff. And my context switches watching short-form content
on a mobile whilst commuting, to enjoying a film on my TV at home.
It’s difficult enough to get personalisation right for a single person. But when that person
has multiple moods, modes and contexts, the challenges of getting personalisation right at
that moment multiply very quickly. And we all have many such states. We all ‘have our
This is where machine learning comes in. Looking at very large data sets and identifying
appropriate outputs not just for the individual, but for the individual’s mood, mode and
context, produces a huge leap forward in the value of personalisation. Presenting something
that is relevant to my interests is valuable. Presenting something that’s specific to my mood,
mode and context is invaluable.
Dealing with ever-changing moods is challenging. So The Filter has adopted an approach of
explaining why certain recommendations might work for certain moods. Taking the idea of
“because you liked …” a step further. And using machine learning to use multiple signals like
time of day, device, day of the week.
That’s why The Filter started out 15 years ago using machine learning for music and media
businesses. It’s what has driven our success in working for some of the world’s largest
media companies during that time, from Vudu and Warner Brothers in the USA; BT TV,
UKTV, Nokia and Orange France in Europe, to SBS in Australia.
In recent years, machine learning has become widely adopted by the OTT sector. We’re
excited by the prospect of more companies recognising the transformative effect that
machine learning can have. It’s The Filter’s long track record that enables us to use machine
learning to get closer to the right recommendation or action for a combination of mood,
mode and context, so we move the definition of personalisation beyond the person alone.