Oracle Unity Customer Data Platform intelligence workbench models catalog

Account lead scoring model

The account lead scoring model is a predictive, ready-to-use data science model that scores B2B accounts on their likelihood of conversion using their profile, revenue, behavior data, and engagement pattern. The scores identify the propensity for accounts to make purchases.

Benefits

• Proactively nurture the right accounts with higher conversion chances.
• Increase the effectiveness of account-based marketing (ABM) efforts.
• Increase the number of marketing-qualified leads (MQLs) and conversion rates.

Industry use cases

• Manufacturing: A global manufacturing company can use Oracle Unity’s predictive, account lead and contact scoring models to estimate and score the likelihood of a sale converting based on profile and engagement patterns.
• Technology: A technology company can leverage predictive account scoring to accelerate ABM efforts by identifying which contacts in a given account have the highest chance at conversion and then proactively add them to campaigns and outreach programs.

Contact lead scoring model

The contact lead scoring model is a predictive, ready-to-use data science model that scores contacts on their likelihood of conversion using their profile, revenue, behavior data, and engagement pattern.

The model generates lead score values with lead score timestamps for every contact. It helps to determine the contacts who are active in different levels of the sales funnel and their potential to make purchases, enabling you to precisely target customer segments and effectively align sales and marketing strategies.

Benefits

• Proactively nurture contacts with higher chances of conversion.
• Increase the number of marketing-qualified leads (MQLs) and conversion rates.

Industry use cases

• Technology: A business software company can leverage this model to accelerate sales efforts by identifying which contacts in a given account have the highest chance at conversion and then proactively add them to outreach programs.

Customer lifetime value model

The customer lifetime value (CLV) model is a ready-to-use data science model that estimates a customer's value over a specific time period. This prediction is based on multiple touchpoints, including customer profile data, past transaction history, and the transaction's monetary value and frequency.

Business users can customize the CLV model to give their customers three, six, or twelve months of lifetime value.

Benefits

• Budget marketing expenses more effectively when acquiring, retaining, and serving customers.
• Identify and focus more on high-value customers to increase customer retention and grow revenue.

Industry use cases

• Consumer packaged goods: An online cosmetics company uses the customer lifetime value model to estimate a customer’s value over time based on their profile and transaction patterns. They create a campaign for a new, high-end skin care product targeted at customers who have bought less than two skin care products in the last six months and spent over $200.
• Automotive: An automotive manufacturer leverages the CLV model to identify customer spending ranges and tailor offers for cars that are within those spending ranges.
• Retail: A grocery store runs the CLV model to identify customers that have high lifetime value with the brand to include in a campaign to promote their new loyalty program.

Campaign revenue attribution models

The campaign revenue attribution models are ready-to-use data science models that help you determine the success of campaigns by analyzing the touchpoints that lead to sales and conversions. There are two types of campaign revenue attribution models.

• The revenue campaign attribution model measures the effectiveness of campaigns by assigning a monetary value to each campaign.
• The non-revenue campaign attribution model measures the effectiveness of campaigns by assigning a percentage attribution value to each campaign. The model calculates an attribution percentage as a percentage value of campaigns converted to total conversions for each individual campaign.

Each model considers all the touchpoints that contributed to the conversion of the campaign.

Benefits

• Understand the attribution beyond revenue-based output.
• Make decisions based on objective data analysis instead of subjective choices.
• Understand which events generate the most effective conversions and determine where to spend budget and improve ROI.

Industry use cases

• Retail: A retailer can use the campaign attribution model to help better understand multichannel journeys and gain insight into which channel is helping drive the most conversions.
• Technology: A SaaS technology company can leverage the campaign attribution model to help better understand multi-touch campaigns and which content, channels, and campaign efforts were the most influential to closing revenue.

Recency, frequency, and monetary model

The recency, frequency, and monetary (RFM) model is a ready-to-use data science model that generates numerical scores for recency, frequency, and monetary values based on event and transaction data. With it, you can segregate customers into various personas and then target them with the most relevant messaging.

The RFM model uses the following characteristics to measure engagement and purchase behavior:

• Recency: The customer’s most recent transaction.
• Frequency: How often does the customer make a transaction.
• Monetary: Size/total value of the customer’s transaction.

Each characteristic is represented by a score between one and five: one is the least recent, least frequent, or lowest purchase value and five is the most recent, most frequent, or highest purchase value.

The model uses the following personas to indicate the value of each customer.

• Lost: Your weakest engagers, with minimum activity in the observed period of time.
• At risk: Engagers who show the beginnings of inactivity and low purchase behavior.
• Can’t lose: Subscribers who have a stronger footprint in inactivity. Still salvageable.
• Promising: Engagers with average recency and value.
• New: Recent engagers with a strong rate of valued engagement.
• Champion: The best of the best. Your most recent engagers with the strongest rate of high value engagement.

Benefits

• Use RFM personas to target your customers with most relevant messages and offers based on the relative customer value. This improved customer engagement can increase response rates, customer satisfaction, customer retention, and customer lifetime value.

Industry use cases

• Retail: A retailer can improve targeting, personalization, and overall conversion by leveraging the RFM model identify and segment audiences (high value, promising, at risk, lost, etc.) for various holiday campaigns based on their past interactions.

Back to top

Churn propensity model

The churn propensity model is a ready-to-use data science model that scores and measures the likelihood of a customer churn based on their transactional and behavioral patterns.

It identifies the customers more likely to churn, giving marketers insight into which customers may want to be targeted with specific campaigns or messaging to retain them.

Benefits

• The model enables you to proactively identify audiences and segments (including high-value customers) at risk of churn. Marketing and advertising teams can then trigger win-back campaigns for these customers with relevant messaging to improve customer retention rate.

Industry use cases

• Communications: A telecommunications provider can automatically send a special promotion to customers who may be thinking about switching to a different provider.

Engagement propensity model

The engagement propensity model measures a customer's likelihood to engage with emails (open, click, subscribe, or unsubscribe) based on their past interactions.

Benefits

• Improve email targeting and campaign engagement.
• Accurately increase campaign touchpoints by focusing on the audiences most likely to engage and remove audiences that may be fatigued.

Product propensity model

This ready-to-use model predicts the likelihood of customers buying a specific product based on historical interactions and customer profile data.

The model enables you to identify which customers are most likely to buy a specific product by looking at the propensity score for customer and product combinations.

Benefits

• Spend marketing budgets more effectively by targeting high propensity customer and product combinations.

Gain insights that wouldn't otherwise be available to your company for improved decision-making.

Industry use cases

• Retail: A retailer can leverage the product propensity model to help identify the right product offers for newly engaged customers to improve conversion and customer acquisition.
• Telecommunications: A mobile communications company can leverage the product propensity model to help guide customers to new phone, hardware, and services upgrades.

Repurchase propensity model

The repurchase propensity model gauges the likelihood of customers repurchasing specific products. Repurchase propensity scores are calculated based on past customer transactions and demographic and behavioral data.

Benefits

• Leverage repurchase propensity scores against audiences created in Oracle Unity Customer Data Platform to optimize cross-channel engagement campaigns and target customers that are most likely to repurchase a product.

Back to top

Next best action model

The next best action model is a ready-to-use data science model that predicts customer needs and recommends the most relevant actions for every customer based on sales and transaction patterns.

The model uses customer profile data, customer engagement, product catalog data, and purchases to generate the top five recommended actions for the customer. You can use these recommendations to determine the most relevant action for a specific customer.

Benefits

• Increase conversion rates by engaging with customers in the right way, with the next, best action on the customers’ journey.

Industry use cases

• Automotive: A global car brand can use Unity’s next best action (NBA) and next best offer (NBO) models to recommend the most relevant actions and offers for every customer based on sales and transaction patterns.
• Financial services: A financial services company can use the next best action and next best offer models to identify audiences that are likely to convert on new offers for financial products, such as an investment account, line of credit, or mortgage, and personalize their customers’ experiences across channels based on that recommendation.
• Travel and hospitality: A cruise line can use the NBO and NBA models to identify which offer to send a customer to help them book their next trip or stay.

Next best offer model

Oracle Unity’s next best offer model is a ready-to-use data science model that predicts customer needs and recommends the most relevant offers for every customer based on sales and transaction patterns.

The model uses customer profile, customer engagement, product catalog, and purchases data to generate recommendations. It enables users to choose from top recommendations on offers tied to various products or services. Users can use these recommendations to determine the most relevant offers to send to specific customers.

Benefits

• Increase your conversion rate by leveraging the next best offer model to engage with your customers with the most relevant content or offer.

Industry use cases

• Automotive: A global car brand can use the next best action (NBA) and next best offer (NBO) models to recommend the most relevant actions and offers for every customer based on sales and transaction patterns.
• Financial services: A financial services provider can use the next best action and next best offer models to identify audiences that are likely to convert on new offers for financial products, such as an investment account, line of credit, or a mortgage, and personalize their customers’ experiences across channels based on that recommendation.
• Travel and hospitality: A hotel chain can use the NBO and NBA models to identify which offer to send a customer to help them book their next trip or stay.

Next best promotion model

The next best promotion model is a ready-to-use data science model that uses customers’ historical product purchases to determine the price a customer is willing to pay for a particular product. Leveraging this model enables you to intelligently personalize the pricing of products for your customers.

Benefits

• The next best promotion model allows for personalized pricing of products which leads to higher conversion rates, total revenue, and average order value.

Industry use cases

• Healthcare: A healthcare company can use the next best promotion model to fine-tune its pricing for a new sleep aid product based on past purchases by individual customers.
• Insurance: An insurance brand can leverage the next best promotion model to deliver personalized pricing for add-on insurance packages to improve conversion rates and help customers bundle and save.

Back to top

Campaign recommender model

The campaign recommender model is a ready-to-use data science model that identifies the most effective campaign to be sent for every customer based on customer's past engagement and conversion trends across different campaigns.

The model uses various timeframes (three months, one year, and three years) to rank recurring and one-time B2C campaigns for every customer in any instance based on the likelihood of conversions.

Benefits

• Improve conversion and ROI on your campaigns by intelligently predicting which campaigns are optimal for customers based on recent engagement and conversion trends.

Industry use cases

• Healthcare: A healthcare organization can leverage the model to identify which future digital patient engagement campaigns are right for each patient based on past conversion and engagement.
• Retail: A retailer can use the model to improve campaign conversion and customer lifetime value by placing audiences in campaigns that they are most likely to engage with based on past engagement and conversion history.

Channel recommender model

This ready-to-use data science model recommends the best marketing channel for customers based on historical interactions data.

The channel recommender model ranks engagement channels for every customer in any instance based on the likelihood of conversions. You get insights into which channels drive revenue and can find opportunities to increase revenue by distributing spend across channels with high conversion rates.

The following channels are assessed:

• Email
• SMS
• Push
• Web

Benefits

• Improve conversion by using the best predicted channel to target customer profiles while they’re moving through the sales funnel.

Industry use cases

• Utilities: An electric utility can use the model to determine whether email, SMS, push, or web is best to communicate with specific customers during on- and off-peak energy hours.

Fatigue segmentation model

This ready-to-use data science model classifies customers into different levels of message fatigue based on their profile and engagement levels.

The fatigue segmentation model helps prevent customer fatigue by offering insights into the number of campaigns and messages that need to be sent to each customer profile.

It measures the message fatigue of every customer profile based on the customer's engagement, history of campaigns received and opened, and most importantly, the persona of customer profile. You determine and control the optimal number of messages to send to each customer profile to avoid fatigue.

Benefits

• Intelligently differentiate customers who are active and ready to engage from the ones who are fatigued.
• Gain insights to help you control the campaign outreach for every customer based on their fatigue levels.
• Increase engagement and/or conversions and decrease dropouts.

Industry use cases

• Manufacturing: A solar panel manufacturer uses the model to classify customers into different levels of fatigue based on their profile and engagement levels. This enables them to adjust the volume of communications to their targeted accounts.
• Technology: A B2B technology company leverages the model to identify potential customers that should be removed from high-touch ABM campaign efforts and placed back into general cross-channel campaigns.

Send time optimization model

The send time optimization model is a ready-to-use data science model that determines the optimal time to send campaign emails to customers based on past email behavior.

For example, the model would trigger sending campaign emails before customers typically check their inboxes. As a result, the message would appear at the top of the customer's inbox, ensuring that the email is most likely to be seen and opened.

Benefits

• Increase customer engagement and conversion by optimizing campaign by targeting customers at the times when they are most likely to see, open, read, or acknowledge emails.
• Send emails just before a customer typically checks their inbox, increasing the likelihood that your emails will be viewed and opened.

Industry use cases

• Retail: A fashion retailer can increase the likelihood of customer engagement and conversion on new campaigns by leveraging the model to improve campaign delivery times across channels.
• Travel and hospitality: A resort can ensure that its weekly low-price vacation deals emails are sent to customers when they are most likely to engage with the content.

Back to top