Data Science



We are firm believers talent is key in Data Science - people with the right Skills, Tools, Mindset and Track-record. We are experts in unlocking the value of data, driving business-relevant insights and providing lasting solutions.


We cover the full spectrum of data management within an organization. We combine datasets from various internal and external sources and create predictive models using R, Python & other software to better signal trends and implications. We deliver agile data science as a service and can quickly ramp up teams, answer questions, test hypotheses and roll-out production-level models.



Some of our data science application areas:


Market Modelling

Analyzes of key drivers for sales and market share performance. Pricing models research & analytics. Estimation of the size of adjacent industries and new opportunities.

  • Robust regression
  • Correlation

Purchase Decision Analysis

Maps decision makers, influencers and purchase drivers in the purchase funnel. Ranks and prioritize drivers for purchase in complex funnels. This enables sales team to target the right stakeholders with the right messages and propositions.

  • Bayesian networks
  • Correlation
  • Covariation
  • Linear Regression Model (OLS)

Multi-Channel Digital & Offline Attribution

Identify contribution to conversion from digital and offline touchpoints (channels). Maximize the impact on both online sales offline sales and allocate budgets across channels to maximize ROI

  • Correlation
  • Linear Regression Model (OLS)
  • Panel Data
  • Bayesian models


Volume forecasting in turbulent or opaque markets. Provides input to sales planning, resource allocation and purchase decision making.

  • HWES
  • ARES
  • Dynamic regression

ROI Analysis

Evaluates business (financial) impact of investments, decisions, or (marketing) actions. Enable resource allocation to best potential actions.

  • Hypothesis testing
  • Linear Regression Model (OLS)
  • Correlations

Predictive Maintenance

Optimize Asset usage and maximize ROI from large Cap equipment through predictive maintenance - minimizing downtime, maximize uptime during peak load periods, minimize repair costs, maximize asset life

  • Neural Network
  • Cumulative Revenue Simulation

Risk Assessment

Assesses risk profiles of customer groups. Quantification of inherent risks, risk mitigation measures and residual risks. Application in e.g. risk based pricing in leasing businesses.

  • Logistics regression
  • Decision trees


Leverage and complete existing datasets by filling in missing values. Through complex simulations this approach allows prediction of the missing inputs with high levels of accuracy.

  • Conditional Random Forest
  • Amelia
  • Bayesian models
  • KNN

Content Marketing

Optimize marketing message content and structure so as to maximize impact on target audience and KPIs (opens, reads, clicks, views, etc.) based on historical data and predictive analytics

  • Robust regression, HWES
  • Bayesian models
  • Bayesian Networks

Retention/ Churn Analysis

Retention / Churn analytics to improve customer value in Service-based industries (telecoms, insurance companies, banks and non-banking financial institutions).

  • Churn Analysis
  • Logistics regression
  • Decision trees

Capacity and Resource Planning

Monitors and analyzes the current demands on resources (e.g. call centers). Analyses drivers for calls and propensity of occurrence considering customer, product, service life cycles and volumes.

  • Linear Regression

Motion and Geospatial Analytics

Extract insights from Customer, Device and Store locations and other spatial data to optimize sales, marketing, distribution, provide bundling, targeted advertising and prioritization of locations

  • Surface analysis, gridding and interpolation methods,
  • Artificial neural networks


Improves sales process and customer satisfaction through better understanding of customer groups and corresponding differences in customer needs.

  • Cluster analysis
  • Decision trees
  • CRM analytics

Customer Life-Time Value Modeling

Modelling and simulating customer progression through product/ service life cycles. Determining value per life cycle stage and drivers for retention and mapping routes to optimize life time value.

  • Cluster analysis (K-means)
  • ROC curve

Individual Level Targeted Marketing

Design the best possible marketing campaign, product offering and pricing for each individual customer based on their historical behavior and predicted future behavior

  • Churn Analysis
  • Logistics regression
  • Decision trees
  • Neural Networks & Machine Learning


Determining the optimum combination of customer perceived value and price. Complemented with views on competitive and substitute pricing models and positions.

  • Conjoint analysis
  • Van Westendorp analysis

Customer Loyalty Modeling

Helps clients identify factors that affect customer experience and ultimately engage/disengage customers causing them to be loyal or abandon company/product/service.

  • Linear regression
  • Correlation
  • LOGIT/PROBIT models

Fraud Detection and Prevention

Help detect and prevent customer and supplier fraud by identifying patterns. Sample data, profile customers, identify red flags, and apply predictive customer behavior.

  • Time Series Analysis
  • Data Mining
  • Neural Networks and Machine Learning