Product recommendations: turning sales data into relevant suggestions

Product recommendation solutions help guide customers and sales teams toward the most relevant products based on real purchasing behavior. Instead of relying on intuition, recommendations are driven by data: what customers bought in the past, which products are frequently purchased together, and how buying patterns evolve over time.

This approach delivers clear business value:

• Improved customer satisfaction through relevant suggestions

• Higher cross-sell and up-sell rates

• Increased average basket size

• Reduced sales cycle time for sales teams

Recommendations can be used across channels: at checkout, in digital platforms, or by sales representatives during customer interactions.

How recommendations are generated

Recommendations are based on historical sales data and customer behavior. Different analytical methods can be applied depending on the use case and data maturity:

1. Association Rule Learning (Market Basket Analysis)

This method identifies products that are frequently bought together by analyzing past transactions. For example:

• Tiles and glue appear together in 25% of all invoices (support).

• Every tile purchase includes glue (confidence = 100%).

• Half of glue buyers also purchase tiles.

These insights form the basis for cross-sell recommendations such as suggesting glue when tiles are added to the basket.

Afbeelding

2. Recommendation systems

This approach looks at average customer behavior:

• What products are usually bought together?

• What did similar customers purchase?

Customers are then shown products that people “like them” often buy, making recommendations more relevant and easier to accept.

3. Predictive modeling

Predictive models estimate the likelihood that a customer will buy a specific product, given their previous purchases. This allows for more targeted recommendations and prioritization of products with the highest chance of conversion.

Practical use cases

• Suggest complementary products at checkout

• Help sales representatives propose frequently paired items

• Enable data-driven cross-selling based on actual buying behavior

Output and delivery

The result is a dynamic recommendation table that lists relevant product combinations and their associated recommendations. This output updates automatically when new orders are placed or when the data is refreshed, ensuring recommendations remain current and accurate.

Afbeelding

By grounding product recommendations in real transaction data, organizations can systematically increase revenue while making it easier for customers to find what they actually need.

Web personalization: creating relevant digital experiences

Web personalization focuses on delivering a tailored user experience across digital platforms such as websites and portals. Instead of showing the same content to every visitor, users see information, recommendations, and messages that are relevant to their profile, behavior, and needs.

This enables:

• More relevant content for each user

• Targeted marketing campaigns

• Up- and cross-selling opportunities

• A clearer, more intuitive user experience

The challenge: limited customer insight

Many organizations struggle to personalize their digital platforms because:

• Past user behavior is not tracked or stored

• There is no user-level behavioral data

• Technology to capture and activate this data is missing

• There is no clear personalization strategy

As a result, all users see the same content, often leading to information overload and missed commercial opportunities.

From generic to personalized: a structured approach

Web personalization starts with building a Customer 360° view by collecting and unifying behavioral and profile data:

1. Tracking user behavior
   The right tools and tracking mechanisms (such as cookies and event tracking) are installed to capture user interactions on the website.

2. Unifying data in a Customer Data Platform (CDP)
   A CDP is used to store and combine real-time behavioral data with customer and profile information, creating a single, consistent view of each user.

3. Data activation
   Based on this unified data, personalized content is pushed to specific users or segments. This includes content recommendations, targeted campaigns, and personalized page elements.

Afbeelding

Concrete example: personalized content at profile level

Consider a user logged into a digital platform. Based on their profile and past behavior:

• Only relevant documents are shown on their dashboard

• Irrelevant or overly complex information is hidden

• Content adapts to their needs without overwhelming them

This ensures users quickly find what they need, while the platform remains focused and easy to navigate.

Afbeelding

Result: better experience and better outcomes

By implementing web personalization supported by a CDP, organizations move from static websites to dynamic digital experiences. Users receive relevant content, marketing becomes more effective, and digital channels become a direct driver of engagement and revenue.

Geo dashboarding: data-driven B2B prospecting by region

Geo dashboarding supports B2B marketing and sales teams in identifying and prioritizing prospecting opportunities across different geographic regions. Instead of working with fragmented data or intuition, teams gain a clear visual overview of where potential customers are located and where sales efforts will have the most impact.

The challenge: prospecting without direction

At NMBS, the B2B team is responsible for closing contracts with companies to provide train subscriptions for employees’ daily work commutes. However, several challenges limited their effectiveness:

• Low data maturity: limited insight into current performance and market potential

• Lack of internal alignment: no shared view on priorities or regional focus

• Inefficient prospecting: no clear guidance on which companies to target

Without data insights or visual overviews, the B2B growth strategy felt like prospecting in the dark.

A data-driven approach to geographic prospecting

Geo dashboarding addresses these challenges by combining multiple data sources into one actionable view:

• Internal sales and customer data

• External data sources such as RSZ/ONSS

• Geographic data on office and employee locations

An algorithm enriches and matches these datasets to identify potential B2B prospects and align them with ongoing sales efforts.

From raw data to actionable insights

Using this approach:

• Over 4 million employees were mapped to their office locations

• The share of employees with a feasible train commute was calculated, based on whether train travel time is equal to or faster than driving

• Current versus potential train commute adoption was calculated per company and per region

These insights are then visualized in an interactive geographic dashboard, showing:

• Where NMBS already has strong penetration

• Where untapped potential exists

• Which regions and companies should be prioritized by sales team

Afbeelding

Result: focused outreach and better alignment

By visualizing prospecting opportunities geographically, B2B teams can focus their outreach on companies with the highest potential, align sales and marketing around the same insights, and move from reactive to targeted, data-driven prospecting.

Contract renewal: predicting renewals and timing

For companies offering fixed-term leasing contracts, understanding whether customers will renew and when is critical. As contract end dates approach, uncertainty often remains about customer intentions. This makes it difficult to plan sales activities, allocate resources efficiently, and retain customers.

Without clear insight into renewal behavior, organizations face several challenges:

• Missed renewal opportunities

• Inefficient sales planning and misdirected dealer efforts

• Higher customer churn

• Unpredictable renewal revenue

As one finance manager put it:
“How can we predict which leasing customers will renew and when so dealers can contact the right customer at the right time?”

A predictive, data-driven renewal process

Contract renewal analytics address this challenge by using historical contract, customer, and behavior data to build a predictive model that estimates:

• The likelihood that a customer will renew their contract

• The expected timing of that renewal

This shifts the renewal process from reactive follow-ups to a proactive, structured approach.

Afbeelding

Turning predictions into action

The model outputs are directly usable by sales and service teams:

• Dealers can prioritize customers with the highest renewal likelihood

• Customers are contacted at the optimal moment, based on predicted timing

• Sales resources are allocated more efficiently across the customer base

Business impact

This data-driven approach delivers clear benefits:

• Proactive customer engagement instead of last-minute outreach

• More efficient use of sales and service capacity

• Reduced customer churn

• Better visibility into renewal behavior and customer lifecycle patterns

Afbeelding

By transforming contract renewals into a strategic, insight-driven process, organizations improve both operational efficiency and long-term customer retention, while making renewal revenue more predictable.