AI Forecasting

Recruitly's forecasting engine typically achieves 85-90% accuracy for most metrics after gathering sufficient historical data from your agency (usually 3-6 months of activity). The system continuously evaluates its predictions against actual outcomes, automatically refining its algorithms to improve accuracy over time. For established clients with longer data histories, forecasting accuracy often exceeds 95% for critical metrics like timeline predictions and revenue projections. Even for new clients, the system provides valuable predictions by applying industry benchmarks while gradually transitioning to your specific performance patterns.

The AI forecasting system analyzes multiple data sources to generate predictions. It examines your historical placement data including success rates, time-to-fill patterns, and revenue outcomes across different job and client types. It considers current pipeline metrics like candidate quality, interview progress, and client engagement signals. The system also incorporates team performance patterns, seasonality factors, and market condition indicators. For Enterprise clients, the system can optionally incorporate external data sources including industry hiring reports, economic indicators, and complementary market signals.

Yes, Recruitly's scenario planning capabilities allow you to create and compare different forecast versions based on adjustable assumptions. You can modify parameters like average time-to-fill, consultant productivity, market growth rates, and fill probability across different categories. The system then generates comparative projections showing how these different assumptions would affect outcomes. This powerful feature enables strategic planning exercises, helps develop contingency plans for various market conditions, and allows you to stress-test your business model against multiple potential futures.

For new role types or markets with limited historical data, the forecasting engine applies a sophisticated approach combining several methods. Initially, it uses industry benchmarks and patterns from similar categories as baseline predictions. It then rapidly incorporates your early performance data, giving increasing weight to your actual outcomes as they accumulate. The system also applies transfer learning principles, identifying which aspects of your existing performance patterns likely transfer to the new category. This balanced approach provides useful projections even for new areas while quickly adapting to your specific performance in that space.

Absolutely. The AI forecasting system includes specialised capabilities for capacity planning and resource optimisation. It predicts future workload distribution, identifies potential capacity constraints or imbalances, and suggests optimal assignment of recruiters to jobs based on specialization, current workload, and historical performance patterns. The system can also model the impact of adding new team members, shifting responsibilities, or reallocating resources between divisions. These capabilities help maximize consultant productivity while preventing both under-utilization and overcapacity situations.