Managing an advertising budget efficiently is crucial for maximizing ROI. Algorithms help automate and optimize ad spend allocation, ensuring the best possible results. This approach relies on structured recipes, which define optimization strategies tailored to different campaign objectives.
Why Not AI Models?
AI models can be powerful for ad optimization, but they come with significant drawbacks:
Cold Start Problem – AI models require large amounts of historical data to learn patterns. New campaigns or small businesses may not have enough data for accurate predictions.
They Are a Black Box – AI decision-making is often opaque. Marketers may struggle to understand why budgets shift, making troubleshooting difficult.
Slow Adaptation – Machine learning models may take time to adjust to sudden changes in consumer behavior, whereas rule-based recipes can be tweaked instantly.
Overfitting Risks – AI can overfit to historical trends, failing to adapt to new audience behaviors or campaign strategies.
Dependency on Platform-Specific AI Systems- Platforms like Google Ads and Meta Ads provide AI-driven budget optimization, but these systems work as "black boxes" and prioritize their own ad ecosystem's revenue. Businesses have limited control over how these algorithms allocate spend.
High Computational Costs - Training and running AI models require significant computational resources. Cloud-based AI optimization tools can be expensive, making them less viable for businesses with tight advertising budgets.
These drawbacks highlight why structured recipes offer a more transparent, cost-effective, faster and adaptable approach to ad budget management compared to full AI-driven automation.
Basic Idea of a Recipe
The core principle of a recipe is to create structured, rule-based automation for ad spend management. Unlike AI models that rely on training data and probabilistic decision-making, recipes use deterministic logic.
Recipe
A recipe in advertising optimization is a structured set of rules and heuristics that determine how budgets should be allocated across campaigns. Unlike AI models, which require vast amounts of historical data and function as black boxes, recipes are transparent, deterministic, and adaptable.
A typical recipe consists of:
Inputs: Key metrics like CPC (Cost Per Click), CTR (Click-Through Rate), Conversion Rate, and ROAS (Return on Ad Spend).
Logic: If-then rules for budget adjustments.
Outputs: Budget recommendations or automated adjustments to ad spend.
Recipes are lightweight, fast, and easier to interpret than machine learning models.
Campaign Tags
To apply optimization recipes effectively, campaigns need to be categorized based on their goals and audience targeting. Common campaign tags include:
TOF (Top of Funnel): Brand awareness, reach campaigns, cold audience targeting.
MOF (Middle of Funnel): Engagement, retargeting users who interacted but haven’t converted.
BOF (Bottom of Funnel): Conversion-focused campaigns targeting high-intent users.
Tags allow the system to apply different optimization strategies based on the campaign’s position in the customer journey
Separate Recipes for TOF, MOF, BOF
Each campaign type requires a different approach:
TOF (Top of Funnel) - Maximize reach and awareness at the lowest CPM
MOF (Middle of Funnel) - Improve engagement and move users toward conversion.
BOF (Bottom of Funnel) - Maximize conversions at the best possible ROAS.
These separate recipes ensure that each campaign type gets the right level of optimization without overspending.
To further enhance efficiency, we can segment each funnel stage into batches based on factors such as audience segments, ad creatives, or geographic regions. This allows us to apply more granular recipes within each level, ensuring even finer budget control and performance improvements.
Daily Modes
Each recipe optimizes for a target metric, such as ROAS (Return on Ad Spend) within an expected range (e.g., 2 to 4). Based on real-time performance, the recipe determines the appropriate mode for the current day:
Stable Mode (Meeting Targets) – If metric is within the expected range, the system continues operating normally, maintaining current budget allocations.
Aggressive Mode (Exceeding Targets) – If metric is higher than expected, it indicates more revenue than anticipated. The system tried to capitalize on momentum and allocates more budget to well-performing campaigns.
Defensive Mode (Below Targets) – If metric is below the target, the focus shifts to minimizing losses. The system reduces spending on underperforming campaigns, and increasing budget on over-performing campaigns only if any.
For added flexibility, these modes can be manually overridden when needed, allowing for adjustments based on external factors or business priorities.
Guard Rails on Budget Limits
Since automated algorithms control ad spend, guard rails help prevent budget waste due to anomalies or misconfigurations. These safeguards ensure spending remains efficient, controlled, and aligned with business goals.
Key Guard Rails:
Recipe-Level Daily Budget Caps
- Configured dynamically based on the daily mode (Stable, Aggressive, Defensive) to allow adaptive flexibility while maintaining control.
Campaign-Level Spend Limits
- Prevents any single campaign from consuming a disproportionate share of the budget.
Campaign Grading
Campaign grading helps assess and categorize campaigns based on performance. It works as follows:
Aggregated Historical Data – Each campaign is scored using aggregated historical performance data.
Configurable Metrics & Time Windows – Different metrics (e.g., ROAS, CTR, CPC) and time windows can be customized for each campaign type to ensure relevant grading.
Categorization – Based on the score and the campaign's mode for the day, campaigns are classified into four categories: Best | Good | Average | Worst
Manual Overrides – Users can manually override the system-generated scores when needed, providing flexibility in campaign management.
Core Heuristics in Each Recipe
Each recipe operates based on four key heuristics to dynamically manage campaigns:
Scale-Up 🚀
Triggered when key metrics (e.g., ROAS, CTR, Conversions) exceed predefined thresholds.
Follows rate limits to prevent excessive or rapid budget increases.
Sunsetting 🌅
Gradually reduces the budget for declining campaigns.
Helps phase out underperforming campaigning instead of stopping them abruptly.
Stop Loss 🛑
Enforces stricter conditions than sunsetting to reduce budget or pause campaigns
Acts as a safety net to cut losses quickly and avoid wasted spend.
Revive 🔄
Re-evaluates paused campaigns to check if they can be resumed if conditions have improved due to late attribution.
Budget Adjustments
The magnitude of budget increases or decreases for each heuristic is configured based on:
Campaign Grade – Higher-performing campaigns receive more aggressive budget increases, while lower-performing ones scale conservatively but receive more aggressive budget cuts.
Deviation from Target Metric – The farther a campaign deviates from the target metric (e.g., ROAS, CTR, Conversions), the stronger the adjustment.
These heuristics work together to maximize efficiency, minimize waste, and adapt budgets dynamically based on real-time performance.
Simple but Effective Strategy to Enable Daily Modes
The algorithm dynamically adjusts campaign grading to enable different daily modes. By modifying the grading strategy, it influences how budget adjustments are applied:
Default Mode – Maintains a balanced distribution across all four grades (Best, Good, Average, Worst).
Aggressive Mode – No campaigns are classified as ‘Worst’, and more campaigns are graded as ‘Best’, leading to larger budget increases across a wider set of campaigns.
Defensive Mode – No campaigns are classified as ‘Best’, and more campaigns are graded as ‘Worst’, resulting in stronger budget cuts and a more conservative approach to spending.
By leveraging this grading shift, the system automatically adapts budget allocation without requiring complex rule-based overrides, making it a simple yet highly effective strategy for daily mode adjustments.
Conclusion
Optimizing ad spend with algorithmic budget management ensures that every dollar is used efficiently while dynamically adapting to campaign performance. By implementing structured recipes, campaign grading, daily modes, and core heuristics (Scale-Up, Sunsetting, Stop Loss, and Revive), advertisers can maximize return on ad spend (ROAS) while minimizing risk.
The approach balances automation with control, offering flexibility through manual overrides and guardrails to handle unexpected anomalies. Additionally, the daily mode hack simplifies decision-making by dynamically adjusting campaign grading, ensuring a seamless shift between aggressive, stable, and defensive strategies.
Ultimately, this system removes guesswork, making ad budgeting more data-driven, adaptable, and effective—leading to better performance, lower waste, and sustained growth in advertising campaigns. 🚀