Anticipate and shape your customers’ next move
Customer Analytics
Today everything feels as though it is in flux. The whole world is changing and shifting at a faster rate than ever before. As for tomorrow, only Nostradamus knows for sure, but by combining and layering your analytical data on customers you can better model their future behaviour. Predictive analytics which uses the latest machine learning tools to predict likely outcomes from combined datasets - whether at an individual level (eg how likely someone is to buy) or a market level (eg the outcome on sales of investment across channels). Predictive models let you identify triggers of likely behaviour, and nudges to encourage desired outcomes. Want to find out who’s most likely to switch away from you, or to turn service subscribers into engaged users? Customer analytics provides the answer.
Customer Predictive Models
Acquiring a new customer is anywhere from 5 to 25 times more expensive than retaining an existing one. So keeping hold of the right customers is critical. Our Churn Risk models identify customers most at risk of leaving, allowing pre-emptive, targeted intervention. We use the latest machine learning algorithms and Natural Language Processing to pinpoint at risk customers. Our models are strengthened by blending a variety of historical data, including customer behaviours, customer touchpoints, customer logs, Net Promoter Score® surveys and more. Whether churn, take-up, or segments, we can produce a snapshot of customer predictions, or embed advanced models in your systems so you can score your customers over time.
Survey Database Tagging
Survey segmentations often fail to deliver to serve existing customers. You may know your key targets, their attitudes and motivations, and therefore the messaging to resonate with them to envoke behaviour changes. But if you don’t have the segments tagged on your database, you cannot actually send the right messages to the right people.
We are often asked to review customer data, evaluate the feasibility of predicting survey segments onto databases, or re-purposing to provide a 360 view segmentation that delivers the motivational element from surveys alongside the behavioural and demographic element from databases. Using machine learning to predict survey segments on your database using just your customer data, enabling you to become more customer centric.
Webscraping, NLP and Machine Learning
Sourcing and scraping online text and imagery, and utilising advances in NLP and machine learning to bring clarity to unstructured data to inform strategy, planning and execution. Either replacing or complimenting primary research to offer rich insights at speed.
As an example, Net Promoter Score® studies are great for understanding your customers, but how do you compare to your competitors? That’s where strat7.ai comes in. We can quickly collect and analyse online conversations about your brand and your competitors. We have corporate API subscriptions to social media and forum data, API access to a lot of websites, and have developed bespoke webscrapers to collect customer review data and forums.
Our advanced NLP and machine learning on unstructured data (text and images) quickly brings clarity and quantifies what people are saying about brands in your category, providing direction on product descriptions, development priorities, and which levers to pull in brand communications.
Market Forecasting e.g. econometric modelling
Making market predictions from a variety of data sources to inform investment decisions. For example, estimating participation, viewing figures, or sales. We are often asked to independently validate advertising spend. We use Marketing Mix Modelling to isolate the impact of advertising spend across channels, distribution data, alongside price, promotion and placement activities to help prioritse future budgets.
Delivery is typically a recommendation report and a scenario planning tools to easily simulate likely outcomes in real-world metrics (e.g., participation, viewing figures, sales).
