In this competition, participants are asked to build a model that predicts the contractor total bid submissions for public construction projects using only information available prior to bid opening. The dataset consists of historical projects with pre-letting job characteristics and the corresponding bid totals. This competition uses anonymized, non-sensitive data and is intended for research and benchmarking purposes only. Each row in the dataset (train_summary) represents a single contractor’s total bid for a single construction project, while the other (train_raw) shows each individual line item bid. Pay-item–level data is provided as auxiliary information and may be aggregated or engineered into job-level features at the participant’s discretion.

Consider external data, such as inflation metrics, cost indices, etc.

 Participants must predict the total bid amount submitted by that contractor for that project. 

**Goal:** The goal of this competition is to develop the most accurate model for predicting total bid amounts.

This is a research and solution oriented competition: collaboration is encouraged, ensembling is allowed, and participants may use external data sources provided they are public, time-consistent, and disclosed.