1. Genesys Altocloud Using AI to shape Customer Journeys
Paul O’Dwyer -
November 2018

2. How AI and machine learning can predict customer behaviour
Gather appropriate data
Including demographic, location, device type and behavioral
Prepare and transform data
Reshape it so that it can be used with a machine learning algorithm
Select the relevant data features
Use built-in techniques to include only the most relevant data features for large datasets
Train, validate and deploy the model
Choose, train and validate from a range of machine learning techniques
Machine learning can predict customer behaviour. Machine learning techniques can be successfully applied to customer data to train high accuracy models, which can be applied in real time to produce accurate, personalized predictions. These insights can prove hugely beneficial to a business looking to engage with the right customers at the right time.
Begin by gathering data about every customer visit to the site. This includes demographic information such as location and device type, as well as behavioral data such as how many pages they have viewed and how long they were on the site.
This step, while often overlooked, is usually the most work-intensive. Now that we have collected relevant data, we must reshape it so that it can be used with a machine learning algorithm.
Large amounts of data collected often results in datasets that consist of 100s of features. This can be detrimental to overall performance of model training and quality of predictions, since some algorithms perform poorly with too many irrelevant features. In such cases, it is advantageous to omit the features that do not add much useful information from the model. This process, known as feature selection, allows for training the models only using the relevant features, hence increasing model building performance and the quality of predictions.
When creating a predictive model, there are various machine learning techniques to choose from. In our case, we are specifically looking at supervised machine learning, where we are constructing a model from labelled training data. The model describes the relationship between the features and the labels and allows us to predict if a customer will get an individual label based on the set of features related to that customer. Currently at Altocloud, we draw from the family of these methods for predicting user behaviour, focusing on the methods that perform well  in binary classification tasks, where we are predicting whether (or not) a customer will achieve an outcome. In this case, techniques such as logistic regression, random forests, or neural networks can be used.

3. The challenge Thousands of calls to your contact center
Millions of online visits
Can you identify and predict when and how to engage with your customers?
Can you shape their journeys for the best outcomes for both you and them?
One of the biggest challenges for the modern business is learning to utilize all of the data available to them in a way that is both meaningful and actionable. However, the potential for using data generated by a website is often left unexplored, and as a result, the intentions and reactions of individual digital customers can be overlooked.
Focus is often placed on the broad strokes - key metrics such as the number of page views this month, or the number of unique visitors. While these figures have their place, we lose the ability to shape our individual customer’s journey, or to identify the customers who need engagement most. As a result, customers who may be on the verge of signing up for a trial, completing a checkout, or any other desirable outcome, can fall through the cracks. We know the outline of the picture, but we are missing all of the shades and complexities needed to understand our customers’ online experience entirely.
On the average website, there is an abundance of information to be collected about who interacts with your site and how. By leveraging all of this data, we can gain insights into customer behavior. Machine learning techniques can be used to determine which customers may be interested in achieving an outcome on your site.
For instance, if a customer is not en route to achieving a desirable outcome, a content offer or a chat offer could help to steer them in the right direction.
<click>
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

4. Smarter Reps – Happier Customers – Better Outcomes
Every agent sees value!
SEE what customers are doing
Observe before, during, and after interactions
NOTIFY team about important customers
Send SMS, desktop alerts regarding important and high-value customers
ACT automatically at best moments
Engage buying interest or need for support
PREDICT needs to improve outcomes
Reduce: interaction handle times, sales cycles
Increase: customer satisfaction, engagement with the right prospects, revenue
Customer Journey Analytics
Intelligence & Machine Learning to Connect the Dots for Real-time Engagement
Predictive Customer Engagement:
Chat, , SMS, Social, Voice, Apps 4
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

5. Who wins? Inside Sales eCommerce Customer Service Marketing
Understand and identify website visitors to enable inside sales teams to reach out at the right moments and control cost of sales.
Inside Sales
eCommerce
Analyze and shape customer journeys with real-time communications and content offers to increase conversion rates and average order values.
Integrate with campaigns and banner ads to qualify and move prospects into the sales pipeline more efficiently and accurately attribute.
Marketing
Customer Service
Improve customer experiences with faster resolutions and make customer service reps smarter and more effective.
 The integration of smart analytics and learning with embedded customer communications opens a range of new customer experience opportunities across a range of business functions that may go beyond current “contact center” thinking, including:
Inside Sales  - understand & identify website visitors and enable inside sales teams to reach out at the right moments to connect through the website and control cost of sales.
eCommerce  - analyze and shape “customer journeys” with real-time communications & content offers to increase conversion rates and average order values.
Marketing  - integrate with campaigns and banner ads to qualify, move prospects into the sales pipeline more efficiently and accurately attribute
Customer Service  - improve customer experiences with faster resolutions and make customer service reps smarter and more effective.
Development Teams can also utilize APIs and SDKs to create tailored solutions with real-time communications leveraging analytics for Line of Business Applications.
<click>
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

6. The Benefits Identify & Engage at Best Moments
Accelerate Revenue Conversion
Improve Customer Experience
Resolve Issues Quickly
Reduce Calls
Increase First Call Resolution
Reduce Bounces & Abandons
Shorten time to respond to customer needs, and provide agents/reps with the right intelligence/insights
Machine Learning and AI make it possible to deliver better results - better quality leads, higher revenue, more satisfied customers without increasing personnel costs.
Identify unique insights about how marketing spend impacts customer engagement and revenue conversions, connect the dots, provide needed visibility
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

7. Demonstration
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

8. How does it work?
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

9. Customer Journey: Events, Context, Insights, Actions
EVENT PROCESSING
EVENT STREAMS
Outcome Probabilities
EVENT STORAGE
MODEL EVALUATION
QUEUES
Web events
Realtime Customer Journey
EVENT STREAMS
BATCH
QUEUES
MODEL LEARNING
Contact Center Integration: Calls, IVR, Mobile App, Social, Message events
EVENT STREAMS
Segmentation
QUEUES
STORAGE
Actions
Ticket, Lead, Generic Events
Web Hook
Vendors
Custom Apps via
RestAPIs, WebHooks
Marketing Automation
CONTEXT
ACTIONS
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

10. Good to know:
Analytics tells you today what happened yesterday so you can plan for tomorrow
Engagement acts on what is happening NOW
All the money you spend on marketing and the digital journey is wasted if you do not have the human touch available at the moment of opportunity.
Genesys confidential and proprietary information. Unauthorized disclosure is prohibited.

11. Thank you