Analytical Module
and Big Data

The module enables real-time data streaming from multiple data sources into one centralized place and uses a wide range of machine learning models to help companies create and foster a Data-Driven Culture.
GET WHITEPAPER

Request a white paper

Did you know that 84% business think that AI will enable them to obtain competitive advantage?

A company that manages to react to customer needs in real time and offer the right products/services on the preferred channel will become the customer’s first choice, and thus emerge as the market leader.

Those that fail to embrace Artificial Intelligence (AI) and the benefits that come from unlocking data, on the other hand, risk being left behind by those that do.

By observing and listening to customer needs, companies can maximize their retention rate, attract new customers, and accelerate into the digital future.

Image module

Did you know that 84% business think that AI will enable them to obtain competitive advantage?

A company that manages to react to customer needs in real time and offer the right products/services on the preferred channel will become the customer’s first choice, and thus emerge as the market leader.

Those that fail to embrace Artificial Intelligence (AI) and the benefits that come from unlocking data, on the other hand, risk being left behind by those that do.

By observing and listening to customer needs, companies can maximize their retention rate, attract new customers, and accelerate into the digital future.

Image module

Process flow

DATA COLLECTION
AND PREOCESSING

Image module

Leveraging immense amount of
collected data for gaining essential
customers insights

ML MODELS
DEVELOPMENT

Image module

Using AI prediction and ML
algorithms with high-performance
measures for finding correlations
between key factors and patterns in
customer behavior

ENHANCING
CUSTOMER

Image module

Providing companies with multi-beneficial
insights about their customers, which
results in better customer understanding,
enhanced personalization and customer
experience, risk minimization, and
reduced expenses

Next best offer

Model for product and service recommendation, Next Best Offer, calculates customer tendency to make a purchase, or inclination to use a certain product or service that company provides. This predictive model makes decisions based on customer’s previous actions and behavior toward the company.

Image module

Next best offer

Model for product and service recommendation, Next Best Offer, calculates customer tendency to make a purchase, or inclination to use a certain product or service that company provides. This predictive model makes decisions based on customer’s previous actions and behavior toward the company.

Image module

Selecta’s success

Image module

NBO model empowers
companies to recognize the
clients who will purchase
their products or services
with 85% reliability.

Image module

Our AI algorithm enables
banks to categorize correctly
over 95% of customers’
transactions and embrace
new, prosperous
opportunities.

Image module

Using machine learning
powers companies with an
immense capability to
identify precisely potential
premium clients.

Image module

NBO model empowers
companies to recognize the
clients who will purchase
their products or services
with 85% reliability.

Image module

Our AI algorithm enables
banks to categorize correctly
over 95% of customers’
transactions and embrace
new, prosperous
opportunities.

Image module

Using machine learning
powers companies with an
immense capability to
identify precisely potential
premium clients.

From unstructured data
to satisfied customer

Selecta is collecting data from all possible sources, whether it is a website visit, an transaction in ebanking, or logs into personal account in the app or website, a conversation with operators from Call center, a chat with a company chatbot, or a simple visit to a shop or branch office. This data is processed and represents inputs for machine learning models. Each of these models have outputs which represents benefit to the company – how to increase sales, retain existing customers, and increase customer satisfaction. Next Best offer model provides a personalized offer for your customers, Segmentation model provides better customer profiling, while Customer Lifetime Value predicts how much a company will have value from each customer.

From unstructured data to satisfied customer

Selecta is collecting data from all possible sources, whether it is a website visit, an transaction in ebanking, or logs into personal account in the app or website, a conversation with operators from Call center, a chat with a company chatbot, or a simple visit to a shop or branch office. This data is processed and represents inputs for machine learning models. Each of these models have outputs which represents benefit to the company – how to increase sales, retain existing customers, and increase customer satisfaction. Next Best offer model provides a personalized offer for your customers, Segmentation model provides better customer profiling, while Customer Lifetime Value predicts how much a company will have value from each customer.

Layer
Layer
Layer
Layer
Layer
Layer

Models

CUSTOMER SEGMENTATION

The main aim of Customer segmentation is to provide a better understanding of customer behavior, as well as tracking movement of the customers between segments. Segments’ characteristics are used for suggesting the company how to approach which customer profile, and migrations between the segments enable tracking customer satisfaction.

CHURN PREDICTION

Churn model will recognize clients who intend to stop using a certain product or service. The goal of this model is early identification of customers who are likely to leave the company, so the company can react and retain them. This information could be available through Selecta’s 360 customer profile, or could be used for sending campaigns to the specific group of clients. The aim of this prediction model is to improve retention rate. When it comes to using churn model in banking, the model recognizes customers who have up to 9 times greater possibility to close current account or leave Primary segment.

EARLY WARNING SYSTEM

We are working on developing an early warning system (EWS) that helps credit risk analysts make quicker and more informed decisions. When banking is concerned, Early Warning System model predicts the status of the bank’s corporate or small business customer for the next 6 months, based on transactions and other types of customer data. This implies that a potential or existing problem in their business can be identified, so it has minimum influence on the bank.

INTELLIGENT TRANSACTION CATEGORIZATION

Machine learning is used for transaction categorization in banking sector. The model enables categorizes customer payments (card and domestic) by using machine learning model. It enables the bank to track and monitor changes in spending categories and provide statistics to the customer through different channels. Furthermore, categories can be used for customer segmentation, understanding of customers’ habits, and personalized approach in terms of products and services bank offers to them.

CUSTOMER LIFETIME VALUE

Customer Lifetime Value predicts the value of a customer for a one-year period. It models customers’ purchasing behavior in order to predict what their future value will be.

PREMIUM CLIENT DETECTION MODEL

Premium Client Detection model enables the company to approach the customers who have the highest probability to become premium with the appropriate offers and shift them to the premium/VIP segment. This model calculates customer tendency to become premium based on his or hers previous behavior towards the company and compares identified behavior with the behavior of the premium customer segment.

SMART FINANCIAL PLANNING

Smart Financial Planning consists of:
» Spending Tendency Detection model
Model tracks changes in customers’ spending behavior. It enables identification of customer hobbies and habits.
» Spending Tendency Prediction
Model predicts customers’ spending on different
spending categories, or subcategories.
» Peer comparison
Peer comparison represents predicting customer’s
needs through comparison with his or her peers (for
example: how to save, product recommendations).
» Overspending prediction
Overspending prediction recognizes time periods in
which customers spend the most.
» Saving Recommendation
Identification of customer’s eligibility for savings.

EVENT HUB SIGNALING

EventHub signaling starts by identification of all events related to a customer. They include life events, work events, lifestyle events and events related to company products. All events represent triggers for signaling that enables the company to create a highly personalized approach, conduct lightweight and precise targeting and to react on time.

Models

The main aim of Customer segmentation is to provide a better understanding of customer behavior, as well as tracking movement of the customers between segments. Segments’ characteristics are used for suggesting the company how to approach which customer profile, and migrations between the segments enable tracking customer satisfaction.

Churn model will recognize clients who intend to stop using a certain product or service. The goal of this model is early identification of customers who are likely to leave the company, so the company can react and retain them. This information could be available through Selecta’s 360 customer profile, or could be used for sending campaigns to the specific group of clients. The aim of this prediction model is to improve retention rate. When it comes to using churn model in banking, the model recognizes customers who have up to 9 times greater possibility to close current account or leave Primary segment.

We are working on developing an early warning system (EWS) that helps credit risk analysts make quicker and more informed decisions. When banking is concerned, Early Warning System model predicts the status of the bank’s corporate or small business customer for the next 6 months, based on transactions and other types of customer data. This implies that a potential or existing problem in their business can be identified, so it has minimum influence on the bank.

Machine learning is used for transaction categorization in banking sector. The model enables categorizes customer payments (card and domestic) by using machine learning model. It enables the bank to track and monitor changes in spending categories and provide statistics to the customer through different channels. Furthermore, categories can be used for customer segmentation, understanding of customers’ habits, and personalized approach in terms of products and services bank offers to them.

Customer Lifetime Value predicts the value of a customer for a one-year period. It models customers’ purchasing behavior in order to predict what their future value will be.

Premium Client Detection model enables the company to approach the customers who have the highest probability to become premium with the appropriate offers and shift them to the premium/VIP segment. This model calculates customer tendency to become premium based on his or hers previous behavior towards the company and compares identified behavior with the behavior of the premium customer segment.

Smart Financial Planning consists of:
» Spending Tendency Detection model
Model tracks changes in customers’ spending behavior. It
enables identification of customer hobbies and habits.
» Spending Tendency Prediction
Model predicts customers’ spending on different
spending categories, or subcategories.
» Peer comparison
Peer comparison represents predicting customer’s
needs through comparison with his or her peers (for
example: how to save, product recommendations).
» Overspending prediction
Overspending prediction recognizes time periods in
which customers spend the most.
» Saving Recommendation
Identification of customer’s eligibility for savings.

EventHub signaling starts by identification of all events related to a customer. They include life events, work events, lifestyle events and events related to company products. All events represent triggers for signaling that enables the company to create a highly personalized approach, conduct lightweight and precise targeting and to react on time.

Image
Next Module
Image
Next Module
Image
Next Module

Get to know
your customers
better.

GET LIGHTPAPER

Request a lightpaper

Saga d.o.o. Beograd
Member of New Frontier Group
64a Zorana Djindjica Blvd.
11070 Belgrade | SERBIA
saga.rs
selecta@saga.rs

Get to know
your customers
better.

GET LIGHTPAPER

Request a lightpaper

Saga d.o.o. Belgrade
Member of New Frontier Group

64a Zorana Đinđića Blvd.
11070 Beograd | SERBIA

saga.rs
selecta@saga.rs