This guide shows how NeuroRadar isolates the impact of each marketing channel on revenue using statistical transformations, regularized regression, and automated model selection. Step 1: Raw Spend This is the actual marketing spend by channel and week. It's the input before any transformation or modeling takes place. Step 2: Adstock (Carryover Effect) Robyn uses adstock transformation to capture the lagged effects of media spend across time. The carryover effect is represented as: Adstock_t = Spend_t + θ × Adstock_{t-1} (θ = 0.7) Step 3: Saturation (Diminishing Returns) This step models diminishing returns of media, using a Hill function: Response = x^α / (γ^α + x^α) Step 4: Ridge Regression Robyn estimates the beta coefficients using ridge regression (L2 regularization). Channels with low predictive value get coefficients closer to 0. Step 5: Apply to All Channels The above steps are repeated for each marketing variable: TV, OOH, Facebook, Search, Newsletter, etc. Step 6: Hyperparameter Optimization Robyn runs thousands of model configurations using Nevergrad to tune adstock, saturation, and regularization parameters. Evaluation is based on NRMSE, Decomp.RSSD, and optionally MAPE. Step 7: Model Selection Models on the Pareto front (best trade-offs) are selected and clustered. Each cluster selects a representative winner used in simulation and reporting. Step 8: Budget Simulations With the final model, NeuroRadar can simulate multiple scenarios: maximizing response for a given spend, or minimizing spend for a target efficiency (ROAS/CPA).

A: NeuroRadar primarily focuses on providing advanced Marketing Mix Modeling (MMM) capabilities using open-source tools and machine learning, specifically built on Meta’s Robyn framework. This allows businesses to make data-driven media decisions across both online and offline channels with transparency, automation, and predictive power. However, while Multi-Touch Attribution (MTA) models, which track and assign credit to individual advertising touchpoints, are not a core feature of NeuroRadar, MTA can be suported if the necessary data is provided

You can refresh the model monthly or weekly. Refreshing keeps the model updated without needing to retrain from scratch, as long as inputs and structure remain the same.

NeuroRadar works best for businesses with at least 5 active marketing channels, including both online (e.g., Facebook, Google, Email) and offline (e.g., TV, Radio, OOH). However, models can be built with as few as 3 channels. although, we can model with different campaings goals as different channels if enough data is provided

We use Robyn to transform media variables with adstock and saturation curves, then estimate coefficients with ridge regression and optimize hyperparameters using Nevergrad.

Ideally, at least 2 to 3 years of weekly data (or a minimum of 80-100 weeks) is recommended to capture enough variation in spend, seasonality, and other factors. More data improves model accuracy and stability.

While model insights are available as soon as the first analysis is complete, most clients observe measurable improvements in ROI and marketing efficiency within the first 1 to 3 months of applying NeuroRadar’s recommendations.

NeuroRadar helps businesses optimize marketing spend to maximize revenue, reduce customer acquisition cost, and allocate budget more effectively across channels for measurable growth.

Yes. You can use default values (like 0.8x or 1x initial ROAS), or set a custom target using the target_valueargument in the robyn_allocator()function

You can choose between maximizing total response, hitting a target ROAS or CPA, or simulating performance under a custom budget

Absolutely. You can define a specific date_rangelike "last_10"to restrict the simulation to that period

Yes. If you don’t specify a date_range, the allocator uses all available model data to generate recommendations

Adstock: A transformation to model the carryover effect of advertising. Saturation: A curve that models diminishing returns of additional spend. ROAS: Return on Ad Spend. Measures how much revenue you get per $1 spent. CPA: Cost per Acquisition. How much it costs to generate a single conversion. Incrementality: The additional value generated by a marketing channel or campaign. Pareto Front: Set of models that offer the best tradeoffs between key metrics like accuracy and stability. Calibration: Adjusting the model based on real-world experimental results. Decomposition: Breakdown of outcome (sales or conversions) by channel or factor. Hyperparameters: Parameters controlling how adstock, saturation, and regularization behave in model training.