AI-driven optimisation of R&D project portfolio selection in the pharmaceutical industry
R&D portfolios in the pharmaceutical industry involve decision-making under uncertainty: high development costs, long lead times, regulatory risks and highly variable probabilities of success characterise every investment.
In practice, projects are often evaluated and prioritised individually. However, a drug pipeline is not a stack of isolated projects, but a combinatorial selection subject to budget, risk and diversity constraints.
Domain
Healthcare / Innovation Management
Objective
Maximising the expected value of the drug pipeline whilst adhering to an annual R&D budget and a defined risk appetite.
Assessment Inputs
Portfolio modelling is based on project- and phase-specific input data, typically:
- Probability of Technical Success (PTS) per project or per development phase
- Peak sales potential as a key value driver
- Development costs per phase (e.g. preclinical, Phase I–III)
- Strategic fit with therapeutic focus (Alignment Score)
Decision model and selection mechanism
To systematically account for uncertainty, the project value is modelled as a stochastically weighted expected value:
Stochastic Scoring: EVᵢ = NPVᵢ × PTSᵢ
Selection is not carried out as an isolated ranking of individual projects, but as a group selection within the portfolio.
A Constrained Knapsack Model determines the optimal project combination under explicit constraints.
This reveals portfolio trade-offs that are often lost in a pure individual prioritisation – particularly in the case of competing budgets, phase-dependent cost structures and risk or diversity requirements.
Constraints
The selection is calculated under explicit constraints, e.g.:
- Annual R&D budget cap
- Maximum number of oncology projects (management of concentration risks)
- Minimum diversity across disease areas
These restrictions ensure that the portfolio is not only value-maximising, but also risk-adjusted and strategically robust.
Technology approach
A hybrid decision-making architecture is employed:
- StratePlan for combinatorial portfolio selection subject to constraints
- AHP (Analytic Hierarchy Process) for weighting strategic criteria and for the structured integration of qualitative factors
Result logic
The result is not a list of priorities, but a consistent pipeline configuration with explicitly modelled properties:
- Maximised expected portfolio value (EV) within budget and risk appetite
- Controlled concentration in therapeutic areas (e.g. oncology limit)
- Strategic fit and diversity as measurable portfolio attributes
- Transparent trade-offs between value, probability of success, costs and strategic orientation
Conclusion
The selection of an R&D portfolio is not purely a valuation problem, but a combinatorial decision-making problem under uncertainty.
Only when expected values, constraints and strategic criteria are brought together in a formal model, can a robust drug pipeline be systematically constructed – and the quality of decision-making measurably improved.
Common Patterns Across Cases
Assessment
Qualitative and quantitative factors are converted into comparable scores – using scales, valuation models or structured expert assessment. The aim is to establish a consistent, decision-ready evaluation basis.
Ranking
Elements are prioritised. However, ranking is rarely the final decision. In complex environments, prioritisation is frequently embedded directly into a combinatorial optimisation process in order to systematically account for interactions and constraints.
Group Selection
The final selection goes beyond a simple ‘Top-k’ approach. StratePlan solves structured selection problems such as knapsack, portfolio or scheduling models and calculates the optimal combination under real-world constraints.
Constraints
Constraints reflect real-world scarcity: capital, time, resources, risk appetite, regulatory requirements, strategic mandates or sustainability requirements. They are an integral part of the decision-making logic.
Technologies
Hybrid use of MCDA methods (e.g. AHP, TOPSIS) for structured evaluation combined with StratePlan for constraint-aware group or portfolio selection.
These cases demonstrate how StratePlan evolves decision-making processes from pure ranking to intelligent, constraint-aware portfolio construction. Evaluation data is translated into actionable, optimised group decisions – aligned with financial, strategic and sustainability-related objectives.
The underlying core logic – structured evaluation → quantitative prioritisation → constrained group selection – scales across different sectors and is adapted in each case to domain-specific success metrics and constraints.
