AWR Automotive – Improving Customer Retention Through Churn Prevention

awr-dt Registered Posts: 2

Team members:

  • Anitha Banu, Senior Data Engineer
  • Dr. Mani Abedini, Data Science Manager
  • Sebastian Samuel, Chief Information Officer
  • Abhiruchi Tiwary, Lifecycle manager
  • Mahesh Rohra, Chief Strategy and Planning Office

Country: United Arab Emirates

Organization: AWR Automotive

The AWRostamani Group has a diverse portfolio of businesses operating across various industries, including Automotive, Real estate, Ventures & Investments. Driven by the purpose of enriching lives, we have grown into a conglomerate of many companies with presence in seven diverse sectors and strive to help shape a better world with our exceptional products and services.

Here are some key sectors and companies under the AWRostamani Group:

Automotive: The largest Business unit of the group and the leading automobile dealer in the region, ‘Arabian Automobiles’ creates hundreds of happy customers daily and offers complete after sales service with genuine spare parts and car care products. The group operates several automobile dealerships, representing brands such as Nissan, Renault, Infiniti in the Dubai northern Emirates in UAE.

Real Estate: The AWRostamani Group is involved in real estate development and property management. They have been engaged in various residential and commercial projects in Dubai.

Ventures: Our ventures arm include BCD Travel, AWR Lifestyle, KAR Freight and forwarding, AWR Lumina and AWR Logistics.

Investments: AWRostamani Group has a large and diversified local and global investment portfolio, with a primary focus on capital appreciation and dividend yield.

Awards Categories:

  • Best Acceleration Use Case
  • Best ROI Story

Business Challenge:

We proudly stand as one of Dubai's premier automobile dealers, renowned for representing the most sought-after brands in this thriving region. Our after sales services for customers is the solid revenue generator for our business.

Since capturing new customer is multiple times more expensive than retaining existing ones, it has become very important for us to understand customers behavior and prevent churn.

The most challenging part of retaining customers is to identify those who are likely to churn, as well as to reach out at the right time, so that the business doesn’t lose any revenue opportunities. As customer behavior is dynamic, it is all the more complex to understand and predict.

It is also important to effectively manage the cost of retaining customers, since running retention campaigns on inappropriate contacts will lead to further loss of resources and revenue. We therefore set out to define the most accurate segment of customers on the brink of churning.

Our end goal was to proactively take measures against churn by running specific campaigns targeting the right customers and retain them – in turn improving customer satisfaction, loyalty, and long-term profitability.

We set out to build predictive analytics to solve this. Collaboration was established between our Data Science team, the Business Excellence department, Group Customer Experience, and the beneficiary Service Department.

Business Solution:

We have chosen Dataiku as our platform for the use case, from feature engineering until deployment. The versatile platform empowered us to build the end-to-end use case by offering data integration, preparation, machine learning capabilities, visual analysis, automated training, deployment & redeployment based on best accuracy scores, etc.

Our first challenge was to understand customers based on their behavioral patterns. We started by analyzing all customers and their vehicle transactions, including demographics, recency, frequency, feedback and ratings, sales and service history, etc.


Dataiku made this process much simpler for us, through handling all sets of customer data. We were able to make use of built-in recipes to quickly perform feature engineering and cleanups.

We then leveraged the built-in clustering algorithms to identify patterns, before applying a prediction model to yield better results. We also used Dataiku auto feature selection as well as correlation analysis to select most important feature for building the predictive model.

Model retraining is now scheduled once a month. It targets customers who are overdue for service with us, in order to predict if they will return for service or not within a fixed period of time. The prediction results are pushed back as batches to our data lake (GCP Big Query) daily to power marketing campaigns.

Dataiku also helps us redeploy the most accurate model after retraining every month, which eases our model maintenance activity.

Key capabilities from Dataiku on this journey include:

  • Best compute capabilities using Kubernetes
  • ETL pipeline development on the go
  • Feature engineering at fingertips
  • Version control
  • Automated training and redeployment of best model
  • Shareability of reports and project across team and business users
  • Metrics, check and notifications

Business Area Enhanced: Supply Chain/Supplier Management/Service Delivery

Use Case Stage: In Production

Value Generated:

The predictive analytics use case implemented in collaboration with Dataiku has generated more revenue for AWR Service Department through reducing churn by 2%, which leads to additional revenue for the company and saving customer acquisition cost.

We are now able to focus on customers with a high probability of churning (above 90%). The model is directly integrated with our campaigns tool, so that the Marketing team can quickly spin up new offers, such as special discounts on services.

As the project was finalized recently and performance measurement relies on mid-term customer behavior (i.e. coming back for servicing their cars), we will be able to compute ROI more precisely in a few months.

We have already seen a significant increase in leading indicators of campaign performance and a reduction in human errors, which used to miss churn customers.

Value Brought by Dataiku:

  • End to end integrated data science platform.
  • Streamlined model maintenance and deployment/redeployment at scale using Kubernetes.
  • Enhanced team collaboration and data utilization
  • Efficient resource allocation

Overall, the predictive analytics use case has empowered the AWR Service Department to take a proactive and data-driven approach to customer retention. By leveraging data insights and predictions, the business can deliver personalized experiences, enhance customer loyalty, and ultimately drive long-term profitability.

Value Type:

  • Reduce cost
  • Increase revenue
Setup Info
      Help me…