At PayLead, we are convinced that technology should be simple, and smart. It’s with these core beliefs in mind we decided to build our Smart Ranking feature.
Smart Ranking in a nutshell: Smart Ranking is a personalized recommendation engine for consumers. Its recommendation system analyzes millions of data points drawn from users’ transaction history, and suggests products with a high likelihood of being approved and adopted by these users. Smart Ranking automates recommendations that help our clients build a long-term, high-yield relationship with their customers.
The advertising industry is undergoing drastic changes
Back when PayLead was still in the idea stage, we already knew one thing: limiting the advertising pressure applied to customers would be one of the pillars of our mission.
We had the intuition that the future of marketing would be increasingly tailored to the needs and preferences of individual consumers. People no longer respond to generic, mass advertising. They want to be advised, helped, and relate to brand messages.
We know that consumers' attention spans are constantly being stretched thinner and that the entire advertising system (including digital ads) can be overwhelming and come across as a never-ending assault on people’s senses. Every second, our attention is challenged. Brands are fighting to stay on the minds of consumers, and engage with us.
Convenience as a Product
Today, building a simple and enjoyable user experience is key to finding a place in consumers' hearts.
PayLead’s Smart Ranking is quite easy to understand: based on each customer’s preferences, it pushes the best and most relevant promotions and offers from retailers.
Customers enjoy a seamless experience: they simply need to check their reward application / loyalty program, and instead of being confronted with a complex website, loaded with irrelevant information, which may look like this…
…they get a personalized display of brand offers and campaigns in descending order starting with the promotions yielding the highest probability of conversion.
The three pillars of Smart Ranking
How did we come up with this conversion probability?
First of all, if you don’t already know, PayLead excels in transaction analysis: we gather, clean and leverage anonymous transaction data.
And by leveraging, we mean computing different indicators, such as:
The Distance Score
The relevance is measured and determined for each customer.
Paylead Acquisition Campaigns address both online and offline channels, so the first thing to determine is:
- If the campaign is happening in-store, is the customer close to one of the brand locations? We want, by all means, to avoid pushing a campaign for a Parisian restaurant to people living in Marseille, for example.
- If the campaign is happening online, is the customer interested in online shopping? If not, we will downgrade online campaigns
The Brand Love Score
Netflix tells you which movie you will love… Tinder tells you which person you will love… Spotify tells you which song you will love… …PayLead’s Smart Ranking tells you which brand you will love!
Our team developed an in-house recommendation system, based on users’ consumption patterns to guess which Brand they already like, and which ones they are going to love.
This score is calculated for each potential or existing customer.
The Generosity Score
The Generosity Score focuses on the offers themselves: it is generated from the intrinsic quality of the campaign created by the merchant. In order to define it, we take into account:
- the value of the discount offered (in %)
- a timing factor (we give more weight to the most recently created offers, as they benefit from a novelty and desirability effect among customers)
From these 3 scores, we create a global score, which is the conversion probability.
A continuous learning Loop
Our recommendation engine improves collected data, that takes place before and after the customer purchase, creating a self-sustaining, ever-improving environment.
Recommendation systems are becoming increasingly integrated into all aspects of customers' daily lives and companies' decision-making processes. This phenomenon is evident in several industries, especially in those where companies are consumer-facing, where the consequences of information overload, rising client expectations and cost reductions are pushing forward the advancement and adoption of recommendation engines.
Ultimately, it serves as both a tool to improve the client experience and maximize the efficiency of advisors.