ADNOC Distribution - Driving Customer Engagement Through Data Driven Promotions & Hyper-Personalization

Team members: 

  • Rahul Kucheria, VP Loyalty & Payments
  • Uday Pratap Singh, Program Manager (Insights & CRM)
  • Awad Ahmed Ali El Siddig, Team Leader - Digital Analytics & Automations Solutions
  • Ahmed Ashraf Fathi, Senior Analyst - Digital Analytics & Automation Solution
  • Husain Shabbir Battiwala, Senior Analyst - Digital Analytics & Automation Solution

Country: United Arab Emirates

Organization: ADNOC

ADNOC Distribution is the UAE's leading mobility retailer, with a network of more than 570 service stations and over 350 convenience stores. ADNOC Distribution’s ambition is to be global mobility partner of choice, an enabler of sustainable mobility and a provider of exceptional customer service.

With a goal to enable, energize and enhance every customer journey at stations, ADNOC Distribution built robust customer and marketing analytics solution and integrated the same with industry leading marketing CRM and hyper-personalization engine. The solution helps ADNOC Distribution to serve its customers with the right promotional offer(s) / communication(s) at right time and on right channel(s) such at the stations and on digital touchpoints like mobile app, digital wallet, email etc. ADNOC Distribution marketing department has also strengthened day-to-day artificial intelligence (AI) and analytics practice for data driven marketing decisions.

Awards Categories:

  • Best Acceleration Use Case
  • Best ROI Story


Business Challenge:

ADNOC Distribution’s objective has been to analyse and better understand customer behaviours and predict their needs accurately to be able to smartly generate personalized promotions, offers and upsell/cross-sell opportunities. However, certain challenges pertaining to technological solutions and platforms prevented us from driving efficiency and accuracy to achieve our objectives

Some of the key challenges are highlighted here as below:

  • Customer data was decentralized on many sub systems and managed in silos.
  • Inability to have customers 360 view by cluster/segments/region to understand revenue patterns, demographics, customers categories (Ex: VIPs, EV charging customers, caffeine addicted, digital natives, etc.)
  • Unavailability of data science solution to perform day to day analysis and build ML model(s).
  • Risk of losing competitive advantage in future due to the absence of key advanced technologies such as AI and advance machine learning, personalization engine etc.
  • Lack of sharp data insights led to low ROI on marketing investments.
  • Low customer engagement due to absence of intelligent relevant and sharp customer targeting

Business Solution:

The team at ADNOC Distribution marketing department adopted a phase-wise structured approach on data analytics and AI journey. The key milestones include:

  1. Investment in analytical / AI intellects (data scientists, data engineers - internal and from vendors) and leveraged industry leading data science solution (Dataiku) from ADNOC group.
  2. Creation of single source of customer information by building a customer data-mart.
  3. Supporting business stakeholders with everyday AI and analysis – hypothesis testing, on-demand analysis, data summarization etc.
  4. Building of ML models to meet customer engagement and experience vision.
  5. Execution and operationalization of ML models.
  6. Integration of ML models (from Dataiku) with marketing technology platform to deliver personalization and next best action / offer (NBA/NBO).

Data Analytics Roadmap - Delivering Right Customer Engagement & ExperienceData Analytics Roadmap - Delivering Right Customer Engagement & Experience

Key milestones include:

  1. Customer 360 View Data-mart

ADNOC Distribution team created “Customer 360 view” Datamart and set up the capability to deliver day-to-day decisioning support through Dataiku Everyday AI & analysis. The customer data-mart includes 300+ customer attributes for over 1.7 million loyalty customers of ADNOC Distribution. We continue to add to the 300+ customer attributes in line with the development of our customer’s life cycle. Some examples of customer attributes are:

  • Calculations Based: Avg. monthly spend, monthly station visits etc.
  • Data Mining Based: Primary station, weekday/weekend preference etc.
  • Machine Learning Based: Customer segmentation, propensity to C-store purchase etc.

Data analysts use customer data-mart to provide customer trends to support business decisioning. Marketing analysts use data-mart to dynamics segments creation for marketing campaigns. Data scientists use customer data-mart variable as input features in ML models.

From Data Silos to Customer IntelligenceFrom Data Silos to Customer Intelligence

2. Machine Learning Based Customer Segmentation and Profiling

ADNOC Distribution developed customer segments based on customer historical purchase behaviour, demographics, and loyalty enrolment and digital channels activity data. The team leveraged Dataiku drag & drop recipe UI and SQL coding interface to come with segmentation schemes. The team utilized sampling, hierarchical clustering, K-nearest neighbourhood ML techniques to perform segmentation.

The segmentation schemes are refreshed every six months and segmentation mapping against customers are pushed to customer-DataMart.  Customer segments are used run segmented marketing campaigns against specific business objective(s), drive segment specific desired behaviour changes, SKU planning across stations etc.

Customer Segmentation Process OverviewCustomer Segmentation Process Overview

3. Predictive / Propensity Models for personalization and Next Best Action / offer (NBA/NBO) delivery

Hyper personalisation and NBO/NBA delivery requires combination of data science and marketing CRM solution. ADNOC Distribution team has built a series of ML models which help deciding right product / offer / communication to customers across various stages if their customer journey

4. ML model(s) operationalization and integration with marketing CRM solution

ADNOC Distribution team understands the importance of consuming ML models outputs for customer related decisions. The team has performed necessary integration(s) between different technology solution in achieving real-time consumption of model outputs. The model scores along with business rules are used to deliver hyper-personalization and next best actions / offers (NBA / NBO).

ADNOC 5.png ADNOC.png

Business Area Enhanced: Marketing/Sales/Customer Relationship Management


Value Generated:

This Project targeted to increase our customer base, generate more revenue through customer engagement & cross/up sell drive repeat business, category adoption/trial and ensure customers stickiness to our brand and services.

Incremental gross profit: The project has delivered incremental gross profit of tens of millions of USD and above in first half of year 2023. ADNOC Distribution’s F&B business has seen significantly impressive category growth, 40%+ conversions from core fuel business to non-fuel business and 30% increase in customer participation on targeted promotion

Improved marketing campaigns ROI: ADNOC Distribution has recorded highest ever ROI from a marketing campaign this year. Data led promotions have delivered up to 11X marketing promotion ROI in recent quarters. The campaign response rates are up by more than 30% (basis prior to solution launch).

Growth of loyalty customer’s spend value: Average spend per customer is up by +18% – one of the important factors has been the precise customer targeting based on the data modelling.

Better understanding of customers: The project has provided ADNOC Distribution with better understanding of it’s consumer profiles, their mobility needs, shopping mission etc. The team is able to identify opportunities at micro segment level and take targeted actions.

Strong data support to organization initiatives: Everyday AI and analysis capabilities enables business stakeholders to have visibility around customer trends, analyse different scenarios pertaining to a business case and hence better decision making.

Speed of decisioning: Significant improvement in turnaround time on descriptive analysis, hypothesis testing to support new business cases. Up to 40% lesser time taken on complex analytics.


Value Brought by Dataiku:

Business Users Friendly Analysis Platform: GUI based analysis features enabled non-technical users (without SQL/Python skills) to perform day-to-day analysis.  

Productivity Improvement for Data Scientists: Quicker ML outputs due to the ability to identify best fit algorithm using Dataiku’s UI-based ML features combined with hyperparameter selection, feature engineering process and result interpretation using various statistics / charts produced.

Ability to Consume Data from Multiple Sources: Dataiku platform has been able to seamlessly consume data from multiple data sources and perform concurrent analysis, thus saving valuable time and data preparation efforts.

Models Operationalization and Integration with 3rd Party Solution: The team has integrated Dataiku and Salesforce CRM personalization engine, this allows consumption of ML model(s) scores in  real-time to deliver hyper personalization thus improving campaign ROI.


Value Type:

  • Improve customer/employee satisfaction
  • Increase revenue
  • Save time
Version history
Publication date:
04-08-2024 03:11 PM
Version history
Last update:
‎08-16-2023 05:14 PM
Updated by: