Dr.Max faced the challenge of replacing an existing dynamic pricing solution that did not take into account key factors such as competitor prices, market share, or product characteristics. The main technical obstacle was low price volatility – historically, only a few price points were recorded for products. Traditional models therefore often underestimated price as a key factor and failed to predict untested prices, leading to problems with non-monotonicity or the false assumption of constant demand even at higher prices, which made correct pricing decisions difficult.
Dynamic pricing for Dr.Max
Client NameDr.Max
Client CountryCzech Republic
- Client typeEnterprise
- IndustryRetail & E-commerce
- Application areasFinance & Accounting, Marketing, Sales & Customer Engagement, Operations & Process Automation
- AI technologiesAdvanced Analytics / Data Science, Forecasting & Time Series Analysis, Machine Learning, MLOps & Model Monitoring, Optimization & Planning
- Business impactsData-Driven Decisions & Planning, New Revenue & Business Models
- Data typesStructured Tabular Data, Time Series
- Delivery modelsCustom Development, Product / Licensed Software, Service / Subscription
- DeploymentsCloud
- Key capabilitiesPlanning, Scheduling & Optimization, Predictive Analytics & Forecasting
- Project stagesScaling / Expanded Implementation
- Solution formsAnalysis, Recommendation, or Report, API / Micro-service Interface, Automated Backend Process, Plugin / Extension for an existing system, Web Portal / Dashboard
Solution Description
Problem description
Solution
Our solution leverages advanced machine learning to connect key factors such as market dynamics and competitor prices, enabling a more efficient and data-driven pricing strategy. The Dynamic Pricing Engine is built on the Databricks platform, automatically integrates necessary data sources, and provides users with full control over the choice of preferred pricing strategy.
Main Users of the Solution
Pricing specialists
Project timeframe (months)
4
Technologies used
Databricks, Azure, Python, SQL
Additional services
- Data collection and pre-processing
- Data governance and data quality
- Ongoing maintenance and retraining of the model
Implementation
Project Owner on the Client's Side
Head of IT / Data / Technology
Participation on the Client's Side
- Business / Product Owner
- Quality, safety, compliance
- End users
Form of Supplier Involvement
Full implementation.
Operation and Maintenance
Operational Model
Joint management
Needed Competencies on the Client's Side
DevOps Engineer
Impact and Results
Qualitative Benefits
Users receive clearly proposed prices with the expected impact on revenue and margin, enabling them to make better, more informed decisions. The entire pricing process also accelerated significantly, with new prices generated automatically every day.
Quantitative Results
Long-term revenue increase of approximately 12% across markets.
Client Feedback
“Thanks to the Datasentics team’s technical expertise and good collaboration, we successfully implemented an AI-powered dynamic pricing solution that optimizes prices in real time. The rollout of the dynamic pricing solution across multiple markets has driven significant revenue growth and improved our market responsiveness.”
Lessons Learned and Recommendations
Key Success Factors
Joined-team approach – Dr.Max Business and Product Owner, with whom we jointly planned the product roadmap. Expert Data Science and ML knowledge on our side.
Biggest Challenges
Poor input data quality. Thorough EDA helped us unify and improve the data.
Recommendation for Others
Off-the-shelf SaaS tools may not always capture all the specifics of an organization’s pricing strategy. In such cases, we recommend a tailored product approach, leveraging existing technical foundations.
Promotion
Demo / Public Resources
- CompanyDataSentics
- Emailinfo@datasentics.com
- Websitehttps://www.datasentics.com
- AddressWashingtonova 1599/17, 110 00 Praha