2025 GenAI Whitepaper

Leading Moving & Storage Technology Firm Automates Pre-Move Inventory Logging with AI-Powered Object Detection on Amazon SageMaker AI

Artificial Intelligence & MLOps

At a glance

Virtual Moving Technologies (VMT) partnered with Caylent to optimize its moving logistics platform with AI-driven object detection and MLOps, achieving up to 85% precision, 84% recall, a 62% cost reduction, and a scalable, automated solution.

Solution Implemented

AI-driven object detection - Upgraded from Amazon Rekognition to DETA and DETR models on Amazon SageMaker AI.

MLOps automation - Implemented scalable pipelines for training, deployment, and model versioning.

Auto-scaling infrastructure - Deployed models with endpoint auto-scaling for cost efficiency.

Data augmentation techniques - Enhanced model generalization for improved object detection accuracy.

CI/CD with Laravel Forge - Aligned with VMT’s development environment for seamless updates.

Outcomes Expected

62% cost savings through reduced monthly inference costs.

Improved object detection precision and recall, up to 85% and 84% respectively.

Auto-scaling and A/B testing ensure reliability and cost efficiency.

Internal Sales teams achieved a 100% productivity increase with AI driven inventory logging.

Company

Virtual Moving Technologies (VMT) offers the most affordable, accurate and easy to use virtual survey solution. Their mobile app allows their customers to video record the areas of their house, apartment or office they wish to move. From the captured videos, an accurate inventory list is generated to allocate the right amount of resources and provide the most precise move estimates.

virtualmovingtechnologies.com

Location

Albany, New York

Industry

Truck Transportation

Share

Revolutionizing the Moving Process with AI-Driven Inventory Management

Think about the last time you moved—sorting through your belongings, estimating how much space everything would take up, and ensuring nothing was left behind. Now imagine doing this on a massive scale, managing thousands of moves, and ensuring accurate inventory management for every customer. Moving companies and logistics professionals face this challenge daily, often relying on outdated, manual processes that require on-site assessments and meticulous data entry. These inefficiencies not only slow down operations but also introduce errors that can lead to miscalculations, delays, and added costs.

With a legacy of over 100 years in the moving and logistics industry, Virtual Moving Technologies (VMT) has consistently adapted to technological advancements to remain competitive. VMT set out to eliminate the inefficiencies of manual inventory tracking through an AI powered system that could accurately detect and classify objects from customer-recorded videos, reducing the need for human intervention.

Initially leveraging Amazon Rekognition, VMT faced issues with accuracy, scalability, and cost-effectiveness which prompted the need for a more advanced solution. VMT partnered with Caylent to leverage Amazon SageMaker AI, building a solution that achieves greater accuracy more efficiently. 

Caylent implemented data augmentation techniques that enhanced the model’s ability to generalize across diverse environments, significantly improving object detection precision up to 85%. This tool has been hugely impactful, helping VMT double sales team productivity, allowing them to conduct up to 12 virtual assessments per day instead of 3-4 in-person visits by significantly reducing travel time and manual effort.

Problem

As VMT evaluated their application, it became evident that their existing AI-powered solution based on Amazon Rekognition, was not delivering the efficiency and accuracy required to scale effectively. Several challenges emerged that hindered their ability to offer a seamless, fully automated inventory management system:

  • Inadequate AI accuracy: The Rekognition model was only able to detect about 60% of objects in customer-uploaded videos, requiring substantial manual intervention to verify and correct the results.
  • High operational costs: The inference costs associated with Rekognition were becoming increasingly prohibitive, making it difficult for VMT to scale its services effectively.
  • Limited scalability and adaptability: Without an automated retraining and deployment mechanism, improving the model was a manual and resource-intensive process, leading to slower iteration cycles and longer development timelines.
  • Manual inventory tracking inefficiencies: VMT’s customers and employees would still have to review and adjust inventory lists manually due to gaps in the AI's recognition capabilities, reducing efficiency and increasing labor costs.

VMT required a more accurate, cost-effective, and scalable AI-powered solution that could provide automated, reliable inventory detection at scale.

Thomas Tama

"This technology is transforming the way moving and logistics companies operate. By integrating AI-powered object detection, we're giving movers a faster, more accurate, and scalable way to manage inventory and accelerate logistics operations. We appreciate Caylent’s expertise and collaboration in making this solution a reality, helping us drive innovation and efficiency in the industry." 

Thomas Tama

CEO

Solution

Caylent collaborated with VMT to design and implement an advanced machine learning solution built using Amazon SageMaker AI, tailored to their unique needs. This initiative combined state-of-the-art AI modeling, MLOps automation, and cloud-native architecture enhancements to maximize efficiency and scalability.

AI Model Training & Optimization

Caylent replaced the existing Rekognition model with an open source model, performing experiments with DETA (DEtection Transformer with Assignment) and DETR (DEtection TRansformer), two object detection models trained on Amazon SageMaker AI. These models were selected due to their ability to handle multiple object classes with improved precision and recall. At the end of experimentation, the chosen model was DETA, for its superior and more reliable detection quality.

To address dataset inconsistencies, Caylent implemented data augmentation techniques, enhancing model generalization and accuracy in real-world moving scenarios.

MLOps, Automation & CI/CD

Caylent built a comprehensive MLOps pipeline to automate model training, evaluation, deployment, and rollback. This included:

  • A training pipeline that facilitated automated training, evaluation, and version control using SageMaker AI's capabilities such as Training Jobs, Processing Jobs, Pipelines and Model Registry.
  • A deployment pipeline, leveraging SageMaker AI's Real-Time Endpoint, enabled seamless rollouts with A/B testing and rollback mechanisms to ensure stability.
  • Endpoint auto-scaling dynamically adjusted resources based on demand, to improve efficiency.
  • Manual retraining triggers, which allowed VMT to refine models with new data, ensuring continuous improvement and adaptability.

To ensure smooth and continuous model updates, Caylent integrated Laravel Forge for CI/CD, aligning with VMT’s development environment and tool choice. This enables their teams to iterate faster and reduce downtime.

AI Business Workflow Integration

Beyond model training, Caylent designed a holistic AI solution that integrated directly into VMT’s business operations. This ensured SLA commitments were met while enhancing the overall customer experience. Additionally, Caylent implemented a customized Label Studio platform, enabling VMT to curate high-quality training datasets, further improving model accuracy over time.

Cloud Architecture & Scalability

To ensure cost efficiency and long-term sustainability, Caylent designed a scalable cloud-native architecture, leveraging AWS-managed services for optimal performance. Key components included:

  • Amazon SageMaker AI for model training, inference, and MLOps automation.
  • EventBridge, Lambda, and S3 for event-driven processing and data storage.
  • IAM policies for secure access control and compliance.
  • Terraform for Infrastructure-as-Code (IaC), enabling repeatable and efficient deployments.
  • ECR-based containerization to support optimized model training and inference workloads.

By implementing these enhancements, VMT’s AI-driven logistics platform is now highly scalable, cost-efficient, and easy to maintain, ensuring the company can seamlessly evolve and adapt to future technological advancements.

Company

Virtual Moving Technologies (VMT) offers the most affordable, accurate and easy to use virtual survey solution. Their mobile app allows their customers to video record the areas of their house, apartment or office they wish to move. From the captured videos, an accurate inventory list is generated to allocate the right amount of resources and provide the most precise move estimates.

virtualmovingtechnologies.com

Location

Albany, New York

Industry

Truck Transportation

Share

Related Services

Caylent Catalysts™

ML Operations with SageMaker

Leverage Amazon SageMaker AI's MLOps toolset to reduce your time-to-market, streamline administrative tasks, lower your operational costs, and free up valuable time for data scientists and engineers to focus on innovation and differentiation.

Caylent Services

Artificial Intelligence & MLOps

Apply artificial intelligence (AI) to your data to automate business processes and predict outcomes. Gain a competitive edge in your industry and make more informed decisions.

Related Case Studies

Venminder Logo

Venminder

Risk Assessment Company Unlocks 70% More Time for Compliance Analysis by Automating Data Retrieval with Generative AI

Read more
Trulioo Logo

Trulioo

Identity Verification Provider Uses Generative AI to Augment Customer Onboarding Experiences

Read more