Sold by: Zabda
Deployed on AWS
Dynamic smart pricing ML model to predict freight cost for spot trucking market
Overview
Data-driven Machine Learning model predicts spot price for freight brokers by considering data inputs from history, live information, current market conditions, customer and carrier profiles to maximize revenue for every load.
Highlights
- * Model uses internal historical data from customer to predict the sell price and overlay with business inputs to present to Carrier Reps with 3 Ranges of price points. Min, Median and Max. * Maximization of price based on Carrier and Customer Characteristics. * Model also uses DAT, FW, SONAR data around Average price per Markets, Load / Truck Ratio,freight Sonar Indices to characterize the Inbound / Outbound markets and adjust the predicted price accordingly
- * Metrics are broken down to measure at carrier and customer level to monitor the effectiveness of suggested prices * Model can be further customized and fine tuned according to the business needs
Details
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
This product is available free of charge. Free subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimensions summary
This listing is free to subscribe, with three ways to run the freight spot pricing model. Two dimensions cover model inference on the ml.m4.xlarge instance type, billed per host hour. One runs in batch mode for grouped predictions, the other in real-time mode for immediate responses. The third dimension charges per inference request instead of by host hour. You choose based on how you consume predictions: pay for the compute time an instance runs, or pay for each request processed. The model generates data-driven spot pricing for freight loads.
Top-of-mind questions for buyers
The host-hour charge covers the time an ml.m4.xlarge instance runs your pricing model. You pay for each hour the instance is active, whether in batch or real-time mode. Billing follows the running time of the compute instance, not the number of predictions produced during that time.
The two ml.m4.xlarge dimensions meter instance run time by the hour, so cost tracks how long compute stays active. The inference.count.m.i.c dimension meters each request processed instead. Host-hour billing suits steady, ongoing workloads. Per-request billing suits intermittent use where you only pay when a prediction runs.
Batch mode processes grouped predictions together, so it fits scheduled pricing runs over many freight loads at once. Real-time mode returns immediate responses, so it fits live carrier rep conversations that need instant spot prices. Both bill per host hour on the same instance type.
www.zabda.com
Helpful?
Vendor refund policy
NA
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
Beta release
Additional details
Inputs
- Summary
All the inputs are mandatory
Distance in KMS i.e. 63.3
Weight in pounds i.e. 43500
order lead time in days i.e. 28.0
OriginPostalcode (US Postal code format - Five digit code) i.e. 38261
destinationPostalcode (US Postal code format - Five digit code) i.e. 38301
example: 63.3,43500,28.0,38261,38301
- Input MIME type
- text/csv, application/json, application/jsonlines
https://github.com/ZabdaTechnologies/Dynamic-spot-pricing-Sample-Notebooks/blob/main/sample_notebook/data/input/real-time/input.csv
https://github.com/ZabdaTechnologies/Dynamic-spot-pricing-Sample-Notebooks/blob/main/sample_notebook/data/input/batch/batchtransform_test_input.csv
Input data descriptions
The following table describes supported input data fields for real-time inference and batch transform.
Field name | Description | Constraints | Required |
|---|---|---|---|
Distance | Distance in KMS
Weight in pounds
order lead time in days
OriginPostalcode (US Postal code format - Five digit code)
destinationPostalcode (US Postal code format - Five digit code) | Type: Continuous | Yes |
Weight | Distance in KMS
Weight in pounds
order lead time in days
OriginPostalcode (US Postal code format - Five digit code)
destinationPostalcode (US Postal code format - Five digit code) | Type: Continuous | Yes |
orderleadtime | Distance in KMS
Weight in pounds
order lead time in days
OriginPostalcode (US Postal code format - Five digit code)
destinationPostalcode (US Postal code format - Five digit code) | Type: Continuous | Yes |
OriginPostalcode | Distance in KMS
Weight in pounds
order lead time in days
OriginPostalcode (US Postal code format - Five digit code)
destinationPostalcode (US Postal code format - Five digit code) | Type: Continuous | Yes |
destinationPostalcode | Distance in KMS
Weight in pounds
order lead time in days
OriginPostalcode (US Postal code format - Five digit code)
destinationPostalcode (US Postal code format - Five digit code) | Type: Continuous | Yes |
Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
GenLogs is the Truck Intelligence™ platform that uses AI across a nationwide network of roadside sensors, satellites, and proprietary datasets to track all U.S. commercial vehicle patterns and drive better business outcomes across trucking, logistics, insurance, real estate, finance, and government.
Detection of similarity of texts using mixed AI and statistical models
XTDB is a SQL database designed to simplify development, reporting and compliance for immutable systems. Featuring: comprehensive auditability with SQL:2011, a modern SQL dialect with PostgreSQL wire-compatibility, support for schema-free document handling, and a cloud native architecture. XTDB offers read-scalable ACID transactions on top of Apache Arrow and S3.
Address your browser automation needs with this Docker-based Grid Server for remote Selenium tests. It queues incoming requests and distributes them to containers automatically. Automate Chrome, Firefox, and Edge concurrently.
Easily connect to Dynamics 365 from AWS Glue
StrongDM is a protocol aware proxy that manages and audits access to databases, servers, clusters, and web apps. StrongDM customers enjoy easy and secure infrastructure access regardless of tech stack or environment.
Customer reviews
No customer reviews yet
Be the first to review this product . We've partnered with PeerSpot to gather customer feedback. You can share your experience by writing or recording a review, or scheduling a call with a PeerSpot analyst.