Our objective was to develop an AI/ML solution that could predict the market price with an accuracy rate of over 90%, helping the client arrive at the best carrier cost and shipper price, leading to optimal margins. The client also aimed to increase the bid-win rate from 1% and to procure better carrier costs, considering lane and load attributes, while offering better shipping prices to boost gross margins per employee.

Futurism developed an AI/ML-based condition monitoring system that automated data extraction from PDF format and converted it into time-series data. The solution had a system administrator who performed activities such as raw data correlation analysis and feature selection, data cleansing (missing value imputation/outlier removal), exploring and analysis of data using charts, automatic labeling of data, and running multiple algorithms to compare KPIs and finalize the best model based on accuracy and error metrics.

The solution also had a system operator who could view the dashboard to get information on the predicted health of an engine and its subsystems based on the latest data. The operator could also perform what-if analysis of the predicted health by changing any of the engine parameters or values.

The AI-based condition monitoring system delivered several benefits, including:

• Engine and subsystem level health predictions at least 72 hours in advance

• Improved accuracy of prediction models

• What-if analysis in case of any change in engine parameter

• Reduced inventory, maintenance, and operational cost

• Enhanced performance and safety of the ship