Enosis Outsourcing logo
EndorsedendorsedCompleted

Cloud-Native Data Pipeline and ML Optimization for Real Estate PM

Services Covered:

Big Data Analytics and Business Intelligence • Custom Software Development
Project hero — replace with case study imagery
Industry
Industry

Real Estate

Duration
Duration

10 months

Budget
Budget

50K - 199K

Start Date
Start Date

1 September 2023

Team Size
Team Size

1-5

Engagement Model
Engagement Model

Onshore

Project Capability Score (PCS)

gauge meter
74/100
Good

Project Capability Score (PCS) estimates how capable Valor Software is of successfully delivering a project like this, based on its past experience, track record, and ability to handle similar work. Learn more about PCS

Client

Skyland Transportation

mapKansas City, United States of America

Project Summary

A real estate project management company engaged Valor Software to optimize an underperforming data pipeline and warehouse. Valor implemented a cloud-native solution on Google Cloud Platform, using Dataflow for real-time ETL and replacing Redshift with BigQuery, and built a custom TensorFlow ML pipeline on GCP’s AI Platform. These changes reduced operational costs, improved analytics speed and accuracy, and produced more accurate recommendations that increased customer engagement and conversion rates. The team communicated effectively and delivered on schedule.

Key Challenges

  • Inefficient data pipeline and warehouse causing slow reporting during peak loads
  • AWS Lambda functions and Redshift were not scaling and increased operational costs
  • Generic ML model produced inconsistent predictions
  • Global teams faced communication challenges due to time zone differences

Project Deliverables

  • Cloud-native data pipeline on GCP
  • Real-time ETL using GCP Dataflow
  • BigQuery as primary data warehouse
  • Custom ML pipeline using TensorFlow on GCP AI Platform

Project Solution

Valor designed and implemented a cloud-native data pipeline on Google Cloud Platform. They moved the analytics stack off AWS, implemented Dataflow for real-time ETL processing, replaced Redshift with BigQuery as the main data warehouse, and developed a custom ML pipeline using TensorFlow on GCP’s AI Platform. The team followed agile methodologies and used tools like Jira and Slack to coordinate across time zones.

Project Outcome

  • More accurate, tailored recommendations from the custom TensorFlow ML pipeline
  • Improved customer engagement and conversion rates
  • Reduced operational costs and improved analytics speed and accuracy
  • Deliverables provided on time with strong communication

Platforms

  • CloudCloud

Tech Stack

  • Apache BeamApache Beam
  • TensorFlowTensorFlow
  • Amazon RedShiftAmazon RedShift
  • AWS SageMakerAWS SageMaker
  • Google Cloud Platform (GCP)Google Cloud Platform (GCP)
  • Google Big QueryGoogle Big Query

Client Endorsement

Overall Review Rating

5star

Timeliness

Cost Rating

Willing to Refer

Quality of Deliverables

“Valor Software's new machine learning model led to more accurate recommendations and improved the client's customer engagement and conversion rates. The team was timely, quick to respond, and highly communicative via Slack and Jira despite different time zones. They delivered a tailored solution.”

Jen Johnson

Project Manager

Note: This endorsement is based on publicly available client feedback from external review sources.

More Projects by Valor Software

See All Projects by Valor Software