what_we_do_taabgaDbTZK0b2sgts0l
what_we_do_6fuTLtqQKy0pJ5AzrDA2
what_we_do_c6wJZuqRnmaCWDA5Kq9q
what_we_do_nFqUXLBTNGwanUoshPig
what_we_do_AKSim1ksSSmPubxbPj65
what_we_do_ncIt97DSRZmfSUECvhI1
The science behind Afiniti

The science behind Afiniti

The Afiniti process starts with a customer’s caller ID or unique identification number. Upon placing a call or making contact with a business through chat, email, or another medium, Afiniti uses this key to start its data-chaining process using a set of pre-determined sources, including call history and CRM data for the caller.

In this process we combine interaction-level outcomes data from our clients with hundreds of internal and external databases through highly complex data joins in order to build a rich contextual data source for each interaction. Using this data, Afiniti deploys specialized machine learning techniques to identify behavioral patterns in customer-representative interactions that lead to success.

We look at all of the interactions from our client’s databases and determine whether or not they were successful. We then analyze all of the contextual data that we have access to (e.g.: demographic data, previous interactions, and any available internal analytics) and use algorithms we have developed to look for patterns which can in some way predict the outcomes (e.g.: if a customer has had multiple unsuccessful calls with customer care, they are very likely to want to cancel).

The number of interactions, however, is relatively low when compared to the number of data points generally required for most AI algorithms, meaning that relying solely on machine learning techniques can lead to unreliable results. In order to solve this, Afiniti has developed highly sophisticated Bayesian analytical methods combined with proprietary heuristics to further refine our algorithms and adapt them to the scarce data environment.

Isolating the causes of a successful interaction is only the first step. We cannot know when a customer will call in, and equally we cannot know which agents will be available. This requires us to run the algorithm in real-time whenever a customer contacts our clients, in order to determine which of the available pairs of customers and reps is most likely to lead to a successful outcome. Afiniti is able to execute this process in under 200 milliseconds making us imperceptible to clients and customers alike.

After determining the most optimal pairing, Afiniti assigns a pair on this basis.

The outcomes of these calls are recorded, and at the end of each day, the ever-improving Afiniti algorithm is updated with our inputs in order to create increasingly successful interactions in the future.

Precisely measured results

Precisely measured results

Afiniti delivers precisely measurable results by adopting a patented approach of alternating Afiniti ON and OFF in short time cycles.

These short alternating cycles provide a clear statistical view as to the benefit that we deliver, regardless of changes in revenue, agent population, consumer behavior, marketing campaigns, technologies, staffing or other variables.

deployment process

Deployment process

Deployment of our technology is led by our global deployment and engineering team. This process typically takes between 25 and 100 days, although it can take as few as five for a client who uses a telephony provider with whom we have a native integration.

Our systems have been integrated in over 55 diverse contact center environments, including Aspect, Asterisk, Avaya, Cisco, Genesys, IEX/NICE, Interactive Intelligence, Noble, Oracle, Queuebuster, and Virtual Hold among other telephony, customer relationship management and ancillary systems. We have extensive experience in providing the customized integrations that our clients require.

We either deploy our system on client premises or host our solution as a secure deployment at one of our facilities, or on the cloud. Afiniti and our clients generally prefer client premise deployments because no data leaves the client’s firewall and the client itself addresses its data privacy and security needs. In some instances, clients prefer the convenience of a secure-hosted deployment.

Our deployments require no operational change within a client’s contact center organization. There is no change required to the client’s recruitment, training, coaching, evaluation, assignment or compensation of agents. Similarly, there is no change to the client’s interactive voice response (IVR), call recording, workforce management or other systems. A client’s skills-based routing systems are also unaffected by deployment of our systems.

Download Technote

Afiniti’s Global Deployment and Engineering team leads structured workshops and design sessions to ensure understanding of the client’s technology environment and data estate. The output of this phase is two documents: a Project Scoping Document (timeline and resource requirements), and a Technical Design Document (master plan for technology integration).

Afiniti builds a picture of all available data resources within its client. We gather historical call outcome data appropriate to the business metric being optimized, and determine a process of nightly data delivery to Afiniti to allow for continual artificial intelligence learning. The output of this phase is a first AI derived estimate of anticipated Afiniti performance.

Afiniti executes detailed discovery on existing skill based routing call flows and develops any necessary integration changes. Afiniti also prepares for the physical connection of Afiniti’s systems to incumbent telephony and other peripheral technologies. The output of this phase is the telephony call flow code, reporting, and modifications necessary for telephony integration.

Afiniti either deploys its integration within a client’s lab environment or within its own. Extensive load testing will occur at this stage, together with an array of test and use cases to ensure a seamless and durable integration. The output of this phase is a Lab Testing Report that details all the testing protocols undertaken and the results, signifying readiness to deploy.

Over a course of one to two weeks, various components of the lab integration are ported into the production environment. This is done with Afiniti operating in a “fail-safe” mode such that calls continue to flow according to their pre-Afiniti protocols. The output of this phase is a full deployment in the client’s production environment with Afiniti only operating in the “fail-safe” mode.

Initially, Afiniti’s systems are run for a five-minute period over a period of known low call volume, such as late night on a weekend. This interval is gradually increased over a period of one to two weeks until Afiniti is running continually. If there are any unanticipated design or deployment issues that are revealed in production, they are corrected at this stage.

After deployment is complete, Afiniti’s GDE and AI teams maintain a close association with their client counterparts in telephony and data. Ongoing cooperation is critical to ensure optimal system performance. Afiniti works with marketing and operations departments to ensure any anticipated shift in consumer or agent behavior is reflected in the AI modeling.

Business model

The Afiniti Business Model

Given that Afiniti’s benefit is precisely measurable, we offer our clients the option of compensating us based on such benefits. We also offer our technology with SaaS pricing, including per-seat, per-agent and enterprise variants.

In the typical Afiniti partnership model, Afiniti’s clients do not bear any hardware, software, or professional services costs, and Afiniti contracts to take a share of the precisely measured incremental impact attributed to Afiniti’s solution.

Afiniti is well versed in structuring such partnership models, with deep experience in the various industry verticals it serves including Hospitality, Healthcare, Insurance, Telecommunications, Utilities and other sectors.

All Case studies
Afiniti University

Afiniti University

Afiniti runs University sessions for new and existing clients to help them gain further understanding of how Afiniti works. Find out more in the video below.

Learn Where It Works