Provide real-time personalized offers based on customer location, device, and usage

Delight customers by delivering real-time personalized and contextual offers

In a highly competitive market, telecommunications companies that prioritize customer experience (CX) have a distinct advantage. And telcos are well-positioned to provide a superior customer experience by capitalizing on the vast amounts of data they collect, including a goldmine of information on customer behavior, preferences, and location. Providing customers with real-time personalized offers based on their location data is one powerful way telcos can improve customer experience—and, in turn, help boost profitability.

Real-time personalized offers are tailored to an individual's specific needs, preferences, and location and delivered in the moment as they interact with a product, service, or platform. The idea is that by providing customers with content and services that are highly relevant to their immediate needs and interests, businesses can enhance customer satisfaction, drive engagement, and ultimately achieve better outcomes, whether that's increased sales or improved customer loyalty and retention.

Businesses can achieve this level of personalization by processing data and applying algorithms to instantly adapt the content, recommendations, and experiences they deliver to the user's current context and behavior. Customers' smartphones constantly transmit location data, which can be collected and analyzed to provide real-time insights. Location data is a particularly powerful tool in the hands of telcos. By combining location data with customer profiles, including demographics and usage patterns, telcos can create a comprehensive view of each user, which they can use to deliver highly relevant and timely offers and services. Integrating data from third-party sources, such as weather data, traffic patterns, and information about local events, can provide additional context for personalized offers. Real-time data analytics plays a crucial role in turning all this data into actionable insights. Advanced analytics tools can process and analyze the information at lightning speed, allowing telcos to make quick decisions and deliver tailored offers in real time.

Real-time personalized, location-based offers can significantly impact customer behavior by making the user experience more relevant and engaging. Here are some examples of the ways telcos can provide highly individualized, contextually relevant customer experiences using a combination of historical user data (such as past interactions, purchase history, and preferences) and real-time data (including location, device type, and current actions).

• Offering international roaming packages to customers traveling abroad or local discounts for users in a specific area
• Identifying network issues and outages to proactively address problems and communicate with affected customers, reducing frustration
• Tailoring services, providing targeted promotions, and optimizing network performance, all of which can give telcos a competitive edge while helping ensure their customers have the best possible experiences
• Offering a data upgrade when a customer's data usage is about to exceed their plan, which can prevent overage charges and delight the customer
• Rolling out loyalty programs that reward customers for visiting specific locations, such as telco stores or partner businesses
• Recommending products that align with what a user is currently browsing or has recently purchased

Mobile marketing, while effective and potentially profitable, can be risky; however, personalization can help reduce the risk. Relevant marketing messages that contain useful information can enhance the customer experience; but irrelevant, untargeted messages become spam and can lead to customer fatigue and churn.

By providing real-time personalized offers based on customer location data, telcos can create a win-win situation, enhancing customer satisfaction and helping to drive revenue growth. This proactive approach simplifies the customer's experience and reduces the risk of unexpected charges, leading to higher satisfaction and loyalty. For telcos with narrowing margins and significant capital investments to make, improving the customer experience with data-driven personalization and location-based offers can also help significantly impact profitability. Location-based personalization can drive revenue growth in several ways.

• When customers receive offers relevant to their current location, they’re more likely to make spontaneous purchases or upgrades.
• Personalized offers keep customers engaged, reducing the likelihood of churn.
• When users feel their telco understands their needs, they’re more likely to stay loyal.
• Targeted offers are more cost-effective than mass marketing campaigns.
• More opportunities to upsell or cross-sell additional services, such as premium data packages or smart home solutions, can help increase customer lifetime value.

When using customer data to deliver real-time personalized offers, telcos must, as always, handle that data responsibly, comply with regulatory requirements, and communicate transparently about data usage. Striking the right balance between personalization and privacy is key to a successful implementation. To achieve this, telcos need a data platform that’s able to deliver consistency, scalability, and performance while ensuring security and providing service and deployment flexibility.

Balance personalization and privacy with a comprehensive data platform

By ingesting, curating, processing, and analyzing data, telcos can provide their customers with real-time personalized offers based on their location. This involves leveraging location data from users' devices, processing it in real time, and then triggering personalized offers.

The architecture presented here demonstrates how we can combine recommended Oracle components to build an analytics architecture that covers the entire data analytics lifecycle and is designed to help telcos and digital service providers deliver real-time contextual offers to their customers and achieve the wide range of business benefits described above.

This image shows how Oracle Data Platform for Telecommunications can be used to improve customer experiences by delivering contextual offers based on their location, usage, and device preferences.

The platform includes the following five pillars:

1. 1. Data Sources, Discovery
2. 2. Ingest, Transform
3. 3. Persist, Curate, Create
4. 4. Analyze, Learn, Predict
5. 5. Measure, Act

The Data Sources, Discovery pillar includes four categories of data.

1. 1. Applications comprises data from CRM, Service, Billing, Usage, and Product Catalogue
2. 2. Business Records comprises data from BSS, OSS, CDR’s, and Purchase History
3. 3. Technical Input comprises data from Network Events, Device Datasets, and Network Quality
4. 4. 3rd Party Data comprises Oracle Data Cloud, Social Data, and Offer Packages

The Connect, Ingest, Transform pillar comprises four capabilities.

1. 1. Batch ingestion uses OCI Data Integration, Oracle Data Integrator, and DB tools.
2. 2. Bulk transfer uses OCI FastConnect, OCI Data Transfer, MFT, and OCI CLI.
3. 3. Change data capture uses OCI GoldenGate.
4. 4. Streaming ingest uses OCI Streaming, and Kafka Connect.

All four capabilities connect unidirectionally into the serving data store and cloud storage within the Persist, Curate, Create pillar.

Additionally, streaming ingest is connected to Streaming Processing within the Analyze, Learn, Predict pillar.

The Persist, Curate, Create pillar comprises four capabilities.

1. 1. The serving data store uses Oracle Autonomous Data Warehouse and Exadata Cloud Service.
2. 2. Cloud storage uses OCI Object Storage.
3. 3. Batch processing uses OCI Data Flow.
4. 4. Governance uses OCI Data Catalog.

These capabilities are connected within the pillar. Cloud storage is unidirectionally connected to the serving data store; it is also bidirectionally connected to batch processing.

Two capabilities connect into the Analyze, Learn, Predict pillar. The serving data store connects to both the analytics and visualization capability and also to the data products, APIs capability. Cloud storage connects to the machine learning capability.

The Analyze, Learn, Predict pillar comprises four capabilities.

1. 1. Analytics and visualization uses Oracle Analytics Cloud, GraphStudio, and ISVs.
2. 2. Data Products, API’s uses Autonomous Data Sharing, API Gateway, and Functions
3. 3. Machine learning uses OCI Data Science, Oracle Machine Learning, and Oracle ML Notebooks
4. 4. Streaming Processing uses OCI Goldengate Stream Analytics, and 3rd Party

The Measure, Act pillar captures how the data analysis may be used: by people and partners.

1. 1. Peoples and Partners comprises Customer Segmentation, Predictive Analytics, Churn Prediction, Dynamic Pricing Models, Cross-Sell and Upsell, Analysis/Prediction, Lifetime Value Prediction.
2. 2. Applications comprises Recommendation Systems/ Location-Based Services, Real-time Behavioral Analysis, and Sentiment Analysis
3. 3. The three central pillars—Ingest, Transform; Persist, Curate, Create; and Analyze, Learn, Predict—are supported by infrastructure, network, security, and IAM.

Connect, ingest, and transform data

Our solution is composed of three pillars, each supporting specific data platform capabilities. The first pillar provides the ability to connect, ingest, and transform data.

There are four main ways to inject data into an architecture to enable telcos to deliver real-time personalized offers.

• To start our process, we’ll enable real-time or near real-time extracts (near real-time ingestion is sometimes referred to as “right-time” ingestion, meaning data is ingested within a time window that enables a customer’s context to be identified and the offer surfaced to them while that context is maintained) to ingest data from enterprise CRM product and offer systems using Oracle Cloud Infrastructure (OCI) GoldenGate. Offer catalog data and availability and eligibility rules data must be ingested in near real time to ensure that opt-out/in and regulatory rules are strictly adhered to. The data is commonly relational in nature and sourced from enterprise applications. OCI GoldenGate uses change data capture (CDC) to detect change events in the underlying structure of the systems that deliver the operational processes that need to be serviced (for example, the creation of a new offer, a customer network issue, the customer using a new device, or taking up a new service, and so on) and sends the data in real time to a persistence layer and/or the streaming layer. OCI GoldenGate provides a CDC mechanism that can process source changes noninvasively by processing the log files of completed transactions and storing these captured changes in external trail files independent of the database. Changes are then reliably transferred to a staging database. The Journaling Knowledge Module (JKM) uses the metadata managed by Oracle Data Integrator to generate all OCI GoldenGate configuration files and processes all OCI GoldenGate–detected changes in the staging area. These changes will be loaded into the target data warehouse using Oracle Data Integrator’s declarative transformation mappings. This architecture enables separate real-time reporting on the normalized staging area tables in addition to loading and transforming the data into the analytical data warehouse tables.
• Next, we’ll enable the bulk transfer of historical operational transaction data for model training and offer-propensity analytics. Bulk transfer services are used in situations where large volumes of data need to be moved to Oracle Cloud Infrastructure for the first time—for example, data from existing on-premises analytic repositories or other cloud sources. The specific bulk transfer service we’ll use will depend on the location of the data and the transfer frequency. For example, we may use OCI Data Transfer service or OCI Data Transfer Appliance to load a large volume of on-premises data from historical planning or data warehouse repositories. When large volumes of data must be moved on an ongoing basis, we recommend using OCI FastConnect, which provides a high-bandwidth, dedicated private network connection between a customer’s data center and OCI.
• The ability to analyze customer location data from multiple sources in real time is critical to serving appropriate and contextual offers. In this use case, we use streaming ingest to ingest all the data read from customer or internal events through mobile interactions, IoT, machine-to-machine communications, and other means. Streams can originate from a variety of internal (network) and external (beacon) sources and can include location data, customer interaction data, movement data, and social media data. Data (events) will be ingested, and some basic transformations/aggregations will occur before it’s stored in OCI Object Storage. Additional streaming analytics can be used to identify correlating location events and initiate sending contextual offers to the customer, and any identified patterns can be fed back (manually) so the raw data can be examined using OCI Data Science.
• While real-time needs are evolving, the most common extract from product, customer, and marketing preference management systems is some kind of batch ingestion using an ETL process. Batch ingestion is used to import data from systems that can’t support data streaming (for example, some legacy billing and rating systems). These extracts can be ingested frequently, as often as every 10 or 15 minutes, but they are still batch in nature as groups of transactions are extracted and processed rather than individual transactions. OCI offers different services to handle batch ingestion, such as the native OCI Data Integration service and Oracle Data Integrator running on an OCI Compute instance. The choice of service would primarily be based on customer preference rather than technical requirements.

Persist, process, and curate data

Data persistence and processing is built on three components. Some customers will use all of them, others a subset. Depending on the volumes and data types, data could be loaded into object storage or loaded directly into a structured relational database for persistent storage. When we anticipate applying data science capabilities, data retrieved from data sources in its raw form (as an unprocessed native file or extract) is more typically captured and loaded from transactional systems into cloud storage.

• Cloud storage is the most common data persistence layer for our data platform. It can be used for both structured and unstructured data. OCI Object Storage, OCI Data Flow, and Oracle Autonomous Data Warehouse are the basic building blocks. Data retrieved from data sources in its raw format is captured and loaded into OCI Object Storage. OCI Object Storage is the primary data persistence tier, and Spark in OCI Data Flow is the primary batch processing engine. Batch processing involves several activities, including basic noise treatment, missing data management, and filtering based on defined outbound data sets. Results are written back to various layers of object storage or to a persistent relational repository based on the processing needed and the data types used.
• We’ll now use a serving data store to persist our curated data in an optimized form for query performance and provide a 360-degree view of the customer. The serving data store provides a persistent relational tier used to serve high-quality curated data directly to end users via SQL-based tools. In this solution, Oracle Autonomous Data Warehouse is instantiated as the serving data store for the enterprise data warehouse and, if required, more-specialized domain-level data marts. It can also be the data source for data science projects or the repository required for Oracle Machine Learning. The serving data store may take one of several forms, including Oracle MySQL HeatWave, Oracle Database Exadata Cloud Service, or Oracle Exadata Cloud@Customer.

Analyze data, learn, and predict

The ability to analyze, learn, and predict is facilitated by three technology approaches.

• OCI GoldenGate stream analytics enables the continuous ingestion of streaming data from sources, including location data. This data is sourced in real time from GPS devices and mobile apps to identify customer location and behavior. This provides an event-driven architecture where data is processed as a series of events. In this case, events represent user movements, geofencing triggers, or any other relevant occurrences. Geofencing events, indicating when a user enters or exits predefined geographical areas, are processed in real time. These geofenced triggers can immediately initiate actions, such as evaluating predefined rules for personalized offers based on the user's current location. The solution allows for seamless integration with external data sources, enriching the real-time analysis with additional context. External data, such as weather conditions or local events, can be dynamically incorporated into the processing pipeline to enhance the relevance and personalization of offers and enable real time reactions, triggering actions and generating personalized offers based on the user's current context and location.
• Advanced analytics capabilities are critical for identifying customer behaviors to inform personalized offers, including uptake propensity and contextual analysis. In this use case, we rely on Oracle Analytics Cloud to deliver analytics and visualizations. This enables telcos to use descriptive analytics (describes current trends with histograms and charts), predictive analytics (predicts future events, identifies trends, and determines the probability of uncertain outcomes), and prescriptive analytics (proposes suitable actions to support optimal decision-making).
• Prescriptive analytics goes beyond predicting outcomes and provides recommendations on the best course of action. Telcos can use prescriptive analytics to understand individual customer preferences, tailoring location-based offers to match their needs and interests. Applying predictive models to historical data, telcos can forecast future outcomes and make proactive decisions. For instance, predictive analytics can help identify the most appropriate offer for a customer and anticipate customer behavior, identify potential opportunities for offers to be contextualized, and optimize offer uptake.
• In addition to advanced analytics, increasingly data science, machine learning, and artificial intelligence are used to look for anomalies, predict where process latency might occur, and optimize the customer journey. For example, machine learning models can be used for context identification, customer segmentation, and personalized marketing. By continuously learning from new data, these models can adapt and enhance their performance over time, leading to increased customer satisfaction and greater profitability. OCI Data Science, OCI AI Services, and Oracle Machine Learning can be used in the databases.
• We use machine learning and data science methods to build and train our predictive models. These machine learning models can then be deployed for scoring via APIs or embedded as part of the OCI GoldenGate stream analytics pipeline. In some cases, these models can even be deployed in the database using the Oracle Machine Learning Services REST API (to do this, the model needs to be in Open Neural Network Exchange format). Additionally, OCI Data Science for Jupyter/Python-centric notebooks or Oracle Machine Learning for the Zeppelin notebook and machine learning algorithms can be deployed within the serving or transactional data store. Similarly, Oracle Machine Learning and OCI Data Science, either alone or in combination, can develop recommendation/decision models. These models can be deployed as a service, and we can deploy them behind OCI API Gateway to be delivered as “data products” and services. Finally, once built, the machine learning models can be deployed into applications that are part of an operational decisioning system (if permitted).
• The final yet critical component is data governance. This will be delivered by OCI Data Catalog, a free service providing data governance and metadata management (for both technical and business metadata) for all the data sources in the data platform ecosystem. OCI Data Catalog is also a critical component for queries from Oracle Autonomous Data Warehouse to OCI Object Storage as it provides a way to quickly locate data regardless of its storage method. This allows end users, developers, and data scientists to use a common access language (SQL) across all the persisted data stores in the architecture.

Use your data to enhance customer experiences and drive loyalty

With support for the entire data analytics lifecycle, Oracle Modern Data Platform gives telcos the tools, performance, security, and flexibility they need to provide customers with real-time personalized, location-based offers. This marketing approach can yield significant benefits for both the customer and the telco, including the following:

• Enhanced customer experiences: Customers receive useful offers when and where they’re most valuable and can accept them with minimal effort.
• Better offer acceptance rates and increased customer lifetime value: Customers are more likely to accept offers they actually want and need, which can help grow sales.
• Improved ability to acquire and retain customers: Superior customer experiences combined with efficient service delivery, competitive pricing, and innovative offerings can help boost customer loyalty and reduce churn.
• Better cost-effectiveness: Targeted offers are generally more successful than mass marketing campaigns, allowing telcos to see a stronger return on their investment.
• Revenue growth: Improving customer loyalty and deepening engagement, expanding targeted cross-selling and upselling opportunities, optimizing marketing spend, and increasing customer lifetime value can all help telcos gain an edge in a competitive market and drive revenue growth.