Studio of Art & Commerce.
How Machine learning sharpens video-marketing performance.
Increased online capabilities mean more and more online users are embracing video, whether they are messaging friends, conducting web searches or even catching up with their favourite influencer.
Users are seeking out increasing amounts of fresh content – giving rise to influencer, or creator marketing. A proven strategy, influencer marketing has delivered an increase in leads for engaged digital brands. It’s the fastest-growing online acquisition channel and its growth is set to continue with industry experts forecasting its growth to £12bn by 2022.
When Studio of Art and Commerce (SOAC), a digital advertising agency in London wanted to capitalise on this opportunity with data-driven decisions, they turned to data pioneers T-DAB.AI (T-DAB) for guidance.
SOAC works with some of the world’s best-loved brands, including HSBC, Boots Alliance, Pepsi Lipton and Inchcape. The agency’s campaigns take many forms: from partnerships with like-minded brands, media partners or relevant public personas to live events and advertising.
Making the most of client budgets is key within any agency and SOAC is no exception. To maximise value, SOAC’s team sought a tool that could accurately predict the engagement levels achieved by online beauty influencer videos across a range of social platforms.
Guided by the team’s industry insights and expertise, T-DAB devised a machine learning strategy and solution that would meet their aims.
The answer was an API-based tool to analyse and predict growth and performance of “explainer videos” produced by digital marketing creatives and vloggers.
Using a range of attributes to quantify video characteristics, such as edginess and uniqueness, unsupervised machine learning models clustered videos to create an understanding of their performance in relationship to others
The production architecture equips YouTube content creators and brand content managers with predictive insights on performance alongside clear guidance on how to drive engagement.
This guidance was further strengthened through trend analysis for the extracted topics. This offers valuable insights into relevancy, trends identified and, most importantly, the remaining growth.
Using these details, together with video meta data, a supervised ensemble model was trained to predict audience engagement. The model features a heterogeneous mix of weak learners, each trained on a unique part of the overall input data. The model type for each weak learner was chosen automatically from several options, dependent on the test accuracy.
The user-friendly solution features an intuitive interactive dashboard offering video-specific insights. Integrated to the database, it provides data relating to a video’s predicted performance on YouTube, performance in relation to other creators, predictions of topic trendiness and much more.
Because content is always being updated, special care was given to its management and storage. The overall data architecture ensures collection and loading processes are automated, while a CI/CD pipeline allows the database to be quickly changed and updated. Video meta data and extracted features, for example, are securely stored on the Microsoft Azure SQL server and readily available for Cognitive Services tools.
The system has delivered huge benefits to two distinct groups of end users: influencers and digital agencies.
The tool allows influencers to upload and test videos before publishing. Machine learning makes it possible to predict their engagement with great accuracy, as well as giving them insights into boosting performance.
For agencies, this tool allows for testing across an entire video campaign. As well as identifying the influencers generating impactful content, the smart system highlights micro-influencers predicted to offer disproportionate engagement.
The system’s sophisticated algorithms predict video engagement accurately up to 75% of the time – giving SOAC the data-driven decisions they need to deliver clients with best value.
ABOut the Data Analysys Bureau
T-DAB.AI is data science and data engineering innovation company. We develop innovative, bespoke machine learning-driven solutions to allow anyone to infuse technology with the spark of predictive intelligence.