Object–relational mapping (ORM) design remains largely driven by fixed heuristics that fail to capture workload-specific tradeoffs among query latency, insert cost, and memory footprint. We present \textsc{Y-Map}, a hybrid neural–symbolic framework for performance-aware ORM schema design that synthesizes \emph{valid} schema candidates and predicts their performance without requiring workload execution at inference time. \textsc{Y-Map} leverages Alloy to enumerate correctness-preserving ORM schemas and ranks them using a multi-encoder regression model that fuses structural, syntactic, and semantic representations with compact schema-level features. By predicting continuous performance objectives, accounting for latency, query latency, and memory footprint, \textsc{Y-Map} enables Pareto-aware selection without per-candidate benchmarking during inference. We evaluate \textsc{Y-Map} on nine object models from e-commerce, banking, and healthcare. Relative to two representative baselines, \textsc{Leant} and \textsc{DTS}, \textsc{Y-Map} yields improved aggregate Pareto quality (GD/HV) while reducing inference time and memory overhead. Overall, the results show that integrating symbolic validity guarantees with learned performance prediction provides a practical, scalable solution for workload-aware ORM optimization.