What is Prescriptive Analytics?
Prescriptive Analytics is the most advanced form of business analytics that goes beyond predicting what will happen to recommending specific actions to take. It uses optimisation algorithms, simulation, and decision science to evaluate multiple possible courses of action and suggest the best option to achieve a desired business outcome.
What is Prescriptive Analytics?
Prescriptive Analytics is the final stage in the analytics maturity spectrum. While descriptive analytics tells you what happened, diagnostic analytics explains why it happened, and predictive analytics forecasts what will happen, prescriptive analytics tells you what you should do about it.
It combines predictions with optimisation techniques to recommend specific actions. For example, a predictive model might tell you that demand for a product will increase by 30 percent next month. Prescriptive analytics goes further and recommends exactly how much inventory to order, from which suppliers, and at what price point to maximise profit given the predicted demand increase.
How Prescriptive Analytics Works
Prescriptive analytics typically involves three components working together:
1. Predictive Models
The foundation is a predictive model that forecasts outcomes based on current conditions. This provides the "what will happen" baseline.
2. Optimisation Algorithms
Mathematical optimisation techniques evaluate thousands or millions of possible actions to find the combination that best achieves the desired objective while respecting constraints. Common techniques include:
- Linear programming: Optimising a linear objective (e.g., maximise profit) subject to linear constraints (e.g., budget limits, capacity constraints)
- Integer programming: Similar to linear programming but with variables that must be whole numbers (e.g., number of staff to schedule)
- Heuristic algorithms: Approximation methods that find good-enough solutions for complex problems where exact solutions are computationally impractical
- Reinforcement learning: AI systems that learn optimal strategies through trial and error in simulated environments
3. Decision Rules and Constraints
Business rules, regulatory requirements, and practical constraints that define what actions are feasible. For example, minimum order quantities from suppliers, maximum delivery times promised to customers, or regulatory limits on pricing.
Practical Examples of Prescriptive Analytics
Dynamic Pricing
A ride-hailing or e-commerce company uses prescriptive analytics to set prices in real time. The system predicts demand for each time period and location, then calculates the optimal price that maximises revenue while maintaining acceptable service levels and competitive positioning.
Supply Chain Optimisation
A manufacturer operating across Southeast Asia uses prescriptive analytics to determine the optimal production schedule, inventory levels, and shipping routes. The system considers demand forecasts, production capacity, shipping costs, lead times, and tariff implications across ASEAN markets to recommend the most cost-effective plan.
Marketing Budget Allocation
A marketing team uses prescriptive analytics to allocate budget across channels (Google Ads, social media, offline media) and markets (Singapore, Thailand, Indonesia). The system predicts the response rate for each channel-market combination and recommends the allocation that maximises customer acquisition within the total budget.
Workforce Scheduling
A retail chain with stores across multiple ASEAN countries uses prescriptive analytics to create staff schedules. The system predicts foot traffic by hour and location, then generates schedules that minimise labour costs while maintaining service quality, complying with local labour regulations, and respecting employee preferences.
Prescriptive Analytics in Southeast Asia
The region presents unique opportunities for prescriptive analytics:
- Complex logistics: ASEAN's geographic complexity, spanning islands, peninsulas, and varying infrastructure quality, makes logistics optimisation through prescriptive analytics particularly valuable.
- Multi-market pricing: Different economic conditions, competitive landscapes, and regulations across ASEAN markets create opportunities for market-specific pricing optimisation.
- Resource allocation: For businesses expanding across the region, prescriptive analytics helps allocate investment, talent, and marketing spend across markets based on predicted returns.
- Regulatory navigation: Prescriptive systems can incorporate varying regulatory constraints across markets, helping businesses optimise operations while maintaining compliance.
The Analytics Maturity Journey
Most organisations adopt analytics capabilities in sequence:
- Descriptive: Dashboards and reports showing historical performance (most organisations are here)
- Diagnostic: Analysis explaining why metrics moved in certain directions
- Predictive: Models forecasting future outcomes
- Prescriptive: Systems recommending optimal actions
You need solid foundations in the earlier stages before prescriptive analytics can be effective. Prescriptive analytics requires reliable predictions, which require good data, which requires good governance. Attempting to skip stages typically leads to failure.
Getting Started
For SMBs considering prescriptive analytics, the path typically involves:
- Master predictive analytics first. You cannot prescribe actions without reliable predictions.
- Identify a decision with clear options and constraints. Pricing, scheduling, and resource allocation are common starting points.
- Start with rule-based optimisation before investing in advanced algorithms. Simple business rules applied to predictions can be very effective.
- Leverage existing platforms. Tools like Google OR-Tools (open-source), IBM CPLEX, and cloud ML platforms include optimisation capabilities.
Prescriptive analytics represents the highest-value application of data analytics because it directly links insights to action. While descriptive and predictive analytics inform decisions, prescriptive analytics automates and optimises them. For businesses operating in complex, multi-variable environments, this can translate into significant competitive advantages.
In Southeast Asia, where businesses often manage operations across diverse markets with different economic conditions, regulations, and consumer preferences, prescriptive analytics helps leaders make better decisions about resource allocation, pricing, and operations. The complexity that makes multi-market management challenging is precisely what makes prescriptive analytics valuable, as human intuition alone cannot optimise across so many variables simultaneously.
For CEOs and CTOs, prescriptive analytics should be viewed as a medium-term goal rather than an immediate project. It requires mature data infrastructure, reliable predictive models, and clearly defined business objectives. However, the organisations that reach this level of analytics maturity consistently outperform competitors in operational efficiency, customer satisfaction, and financial performance.
- Prescriptive analytics requires a strong foundation in descriptive and predictive analytics. Ensure your data infrastructure and predictive capabilities are solid before investing here.
- Start with high-value decisions that involve clear trade-offs and constraints. Pricing optimisation, inventory management, and resource allocation are common entry points.
- Human oversight remains essential. Prescriptive systems should recommend actions for human review, not make autonomous decisions without checks, especially in the early stages.
- Factor in the full context of your operating environment. Prescriptive models for ASEAN markets must account for regulatory differences, cultural factors, and varying market maturity.
- Measure the impact of prescriptive recommendations against previous decision-making approaches to quantify ROI.
- Consider starting with simpler rule-based optimisation before investing in advanced mathematical optimisation or AI-based approaches.
Frequently Asked Questions
What is the difference between predictive and prescriptive analytics?
Predictive analytics tells you what is likely to happen (e.g., demand for product X will increase 30 percent next month). Prescriptive analytics tells you what to do about it (e.g., increase inventory by 25 percent, reorder from supplier A rather than supplier B due to lead times, and raise the price by 5 percent to optimise margin). Predictive is about forecasting; prescriptive is about optimising decisions based on those forecasts.
Is prescriptive analytics realistic for SMBs?
Yes, though typically in focused applications rather than enterprise-wide. An SMB might use prescriptive analytics for a specific use case like marketing budget allocation or inventory optimisation without building a comprehensive prescriptive platform. Cloud-based tools and open-source optimisation libraries have made the technology accessible. The key is having reliable data and clearly defined business objectives.
More Questions
A focused prescriptive analytics solution for a specific business decision typically takes three to six months to implement, assuming predictive models and data infrastructure are already in place. If you need to build predictive capabilities first, add another three to six months. The timeline includes defining the optimisation problem, building and testing models, integrating with business processes, and training users to act on recommendations.
Need help implementing Prescriptive Analytics?
Pertama Partners helps businesses across Southeast Asia adopt AI strategically. Let's discuss how prescriptive analytics fits into your AI roadmap.