The American Journal of Engineering and Technology
98
https://www.theamericanjournals.com/index.php/tajet
TYPE
Original Research
PAGE NO.
98-104
10.37547/tajet/Volume07Issue03-08
OPEN ACCESS
SUBMITED
03 January 2025
ACCEPTED
05 February 2025
PUBLISHED
07 March 2025
VOLUME
Vol.07 Issue03 2025
CITATION
Bulycheva Mariia. (2025). The Automated Competitive Discount
Awareness System. The American Journal of Engineering and Technology,
7(03), 98
–
104. https://doi.org/10.37547/tajet/Volume07Issue03-08
COPYRIGHT
© 2025 Original content from this work may be used under the terms
of the creative commons attributes 4.0 License.
The Automated
Competitive Discount
Awareness System
Bulycheva Mariia
Senior Applied Scientist, Zalando, Germany
Abstract:
The article analyzes the development of an
automated system designed to inform about discounts
offered by competitors on the clothing e-commerce
platform. The main goal was to replace manual data
collection and integration processes with an automated
approach that improves the accuracy of company
pricing steering strategy and reduces operational
overhead. The system model is based on Lagrange
equations, which ensures the integration of price
information into strategic management.
The implementation methodology includes web
scraping through Selenium, scrappy tools, and data
processing using machine learning methods. The
approach to analyzing text materials allows you to
effectively extract meaningful information from
advertising content. The architectural solution is based
on a microservice model, which increases the
adaptability of the system and simplifies scaling. Existing
scientific research, studies, and developments, as well
as the author's practical experience working on a
commercial e-commerce fashion platform, were used as
sources, allowing for a comprehensive exploration of
the topic.
The results demonstrate cost reduction and improved
accuracy of processes related to pricing. The developed
system finds applications in e-commerce, marketing,
data processing, and software development, where
automated solutions for business process management
are in demand.
The study presents a method for collecting and
analyzing data on competitors' price offers. The
developed system uses big data processing algorithms
to monitor changes in pricing policy. This allows you to
quickly adapt pricing strategies, as well as make
adjustments to marketing decisions.
The formulated conclusions confirm the achievement of
The American Journal of Engineering and Technology
99
https://www.theamericanjournals.com/index.php/tajet
The American Journal of Engineering and Technology
the stated goals. The introduction of an automated
approach has made it possible to optimize tasks
related to monitoring and analyzing competitive offers
as well as ensuring pricing steering accuracy, i.e.
meeting certain business targets on total sales
discount rates.
Keywords:
Automation, competitive discounts, pricing
steering, web scraping, machine learning, price
management, and microservice architecture.
Introduction:
E-commerce is evolving within the
context of dynamic market changes, necessitating
prompt responses to shifts in the external
environment. One of the key management strategies
involves analyzing competitors’ pricing policies, with a
particular focus on discounts and special offers. The
data obtained through such analysis helps the
company to ensure an attractive proposition for its
customers relative to the competition, strengthens the
company’s market position and enables adjustments
to pricing strategies.
Traditional
methods
of
collecting
discount
information, which rely on manual processes, are
characterized by low accuracy, high costs, and
dependency on human factors. Big data processing
technologies eliminate these limitations. Automated
price monitoring systems ensure the accuracy, and
speed of data processing, and minimize the likelihood
of errors.
The design of an automated competitive discounts
information system (ACDIS) involves utilizing web
scraping methods, machine learning techniques, and
optimization algorithms. This system handles tasks
related to data collection and processing while
integrating into pricing optimization processes. Its
microservice
architecture
provides
flexibility,
scalability, and adaptability to market environment
changes.
This study aims to develop, describe, and evaluate the
effectiveness of ACDIS for the discount optimization
process. The article also examines the advantages of
employing automated solutions in the e-commerce
sector.
METHODS
Automated bidding systems and auction mechanisms
have been presented in several studies. The work by
Zhang H. et al. [1] describes the structure of
personalized automated bidding systems that account
for individual participant conditions while ensuring
fairness. Y. Xing et al. [5] developed truthful auction
models that guarantee honest interactions. Shenjun
Xue et al. [6] examined time-dependent data and
proposed mechanisms to account for its value under
dynamic conditions. Wen C. et al. [3] investigated multi-
component models where agent interactions through
cooperation and competition create a fluctuating
environment for advertising platforms.
The issue of pricing automation is addressed in the study
by Brown Z. Y. and MacKay A. [2], which examines
algorithms influencing the market. Javed M. A. et al. [4]
proposed a system for generating competitive offers,
enabling more accurate market data analysis. Karlsson
N. and Sang Q. [9] developed algorithms for optimizing
shadow bids in first-price auctions, reducing advertiser
costs.
Automation in e-commerce is explored by James N. et
al. [7], which employs computer vision technologies for
automated calculations. A. Singh and S. Kapoor [10]
studied order automation and price monitoring using
web analytics methods.
Methods applied in recommendation systems and
pricing are discussed in the study by Marchand A. and
Marx P. [11], which implemented a recommendation
system based on user preferences. Ajiteru S. O. et al. [8]
described a web application for automated price
regulation. The integration of auction modules in
electronic procurement is detailed in Bodak B. V. and
Doroshenko A. Y. [12], which outlines approaches to
improving these processes.
An analysis of the literature demonstrates a wide range
of methods for automating bidding and pricing.
However, differences in the definitions of fairness and
honesty
presented
in
publications
complicate
comparisons of their effectiveness. The adaptation of
systems to the specifics of local markets and changes in
consumer behavior remains insufficiently explored. The
lack of integration between bidding automation
technologies and recommendation approaches limits
the potential for their application in comprehensive
solutions.
This study employed an analytical methodology based
on a systematic approach to collecting, examining, and
synthesizing information.
RESULTS AND DISCUSSIONS
The development of an automated system for
intelligent data collection and integration into a larger
optimization system focuses on creating a streamlined
process to take into account competitors’ prices while
solving a revenue maximization problem given the
target growth level. This system structures data,
preparing it for strategic decision-making [1]. The
functionality of the automated system for competitor
discounts integration is detailed in Table 1.
The American Journal of Engineering and Technology
100
https://www.theamericanjournals.com/index.php/tajet
The American Journal of Engineering and Technology
Table 1. Functionality of the Automated System for Competitor Discounts
Integration (compiled by the author)
Functionality
Description
Competitor Price
Monitoring
Automated data collection on competitor prices for targeted goods from
websites, marketplaces, and other sources.
Price Analysis and
Comparison
Real-time comparison of prices for similar goods and services from various
competitors.
Alerts and
Notifications
Notifications about changes in competitor prices or discounts via email, or
within the system.
Demand
Forecasting
Machine learning algorithms to predict future demand changes based on
historical data.
Filter and Search
Criteria Setup
Customizable filters for tracking discounts by product category, brand, region,
and other parameters.
Discount
Effectiveness
Analysis
Evaluation of the impact of competitor discounts on the total sales discount
rate and projected sales and revenue e
Monitoring
Promotions and
Offers
Tracking special offers (discounts, sales, bonuses) from competitors, including
their validity periods.
Integration with
CRM and ERP
Systems
Integration with corporate systems for automatic updates of prices, discounts,
and offers in real-time.
Real-Time Price
Dynamics
Monitoring
Continuous updates on price data in real-time for rapid response to market
changes.
Multichannel
Monitoring Support
Capability to track prices and promotions through multiple channels (online
stores, offline retailers, social media).
Dashboards and
Data Visualization
Visual dashboards displaying prices, discounts, and other data for quick
situation analysis.
Historical Analysis
and Trends
Archiving historical data for dynamic price and discount trend analysis, aiding
in long-term trend identification.
Pricing Strategy
Recommendations
Based on collected and predicted data, the system provides recommendations
for pricing adjustments and promotional activities to enhance competitiveness.
The primary tasks of the automated system for
competitive discounts integration are illustrated below
in Figure 1.
The American Journal of Engineering and Technology
101
https://www.theamericanjournals.com/index.php/tajet
The American Journal of Engineering and Technology
Figure 1. Tasks of the Automated System for Competitive Discounts Integration [1].
The system operates by regularly monitoring
competitors' pricing offers, promotions, and discounts.
In a competitive environment, even minor price
changes by market participants can influence demand
for goods or services, especially for popular items that
are in high demand. Through systematic analysis of
pricing offers, companies can adjust their strategies
promptly.
Data collection employs several methods. One such
method is web scraping, which involves automated
extraction of data from competitor websites. Using
parsing, the system retrieves information about prices,
discounts, promotions, and product listings. In some
cases, data is also obtained through open interfaces
provided by marketplaces, aggregators, or other
services.
Various technologies are used for processing and
storing the collected data. Relational databases like
MySQL and PostgreSQL are employed for structured
information storage, such as data on discounts and
promotions tied to specific products, timeframes, or
geographical locations. For handling large volumes of
data in JSON, XML, or CSV formats, NoSQL-based
solutions like MongoDB are utilized, enabling fast
processing of unstructured data [3, 5, 6].
The system also facilitates comparisons between
external data and the company's internal offers. Based
on the insights gained, recommendations are
generated to adjust pricing or launch promotions
aimed at improving market positions. This feature is
valuable for pricing specialists and marketers
responsible for launching special offers in response to
changes in the competitive landscape.
Data analysis utilizes visualization tools such as Power BI
and Tableau. These tools present information on prices,
discounts, and projected financial data in a clear and
accessible format, aiding in the rapid identification of
trends, decision-making, and responses to competitive
changes. The system also generates reports that enable
tracking sales an
d discounts’ changes over time.
The system can send notifications about significant price
changes or competitor promotions. Notifications are
delivered through various communication channels,
such as email or messaging platforms. This feature is
particularly relevant for companies operating in
environments where pricing policy changes require
swift reactions.
Automating data collection and analysis processes
accelerates the monitoring of changes and reduces the
likelihood of errors that can occur during manual
processing. This automation allows employees to focus
on strategy development and customer engagement,
freeing them from routine tasks [7, 10].
Additionally, such systems can be integrated with other
corporate solutions, such as CRM systems and pricing
management platforms. This creates opportunities for
close collaboration between various company
departments, enhancing overall efficiency. Integration
with a pricing management system enables automatic
adjustment of product prices based on changes in the
market environment.
Platforms supporting distributed computing, such as
Apache Kafka and Spark, are used for analysis, while
data visualization is performed using BI platforms like
T
ask
s
o
f
th
e
a
u
to
m
a
ted
in
fo
rm
atio
n
s
y
ste
m
o
n
co
m
p
eti
tiv
e
d
is
co
u
n
ts
Getting data
Information processing
Price elasticity analysis
Integration with
management systems
The American Journal of Engineering and Technology
102
https://www.theamericanjournals.com/index.php/tajet
The American Journal of Engineering and Technology
Tableau or Power BI. The Automated Competitive
Discounts Information System (ACDIS) is built on a
microservice architecture, which allows it to be
adapted for various tasks [2,4,9]. The main
components of the system are shown in Figure 2.
Figure 2. Main components of the automated competitive discounts information
system (created by the author)
The implementation process of an automated system
for integrating competitive discounts will now be
considered based on practical experience. The
developed solution automates the collection,
processing, and analysis of market price information,
enabling real-time price adjustments. The system is
based on a mathematical model utilizing Lagrange
equations, ensuring accurate approximation of the
optimal solution and consideration of multiple
business targets restricting the solution.
Before the implementation of this technology,
competitive discount data was collected and applied
on top of recommended internal discounts manually,
creating additional technical overhead, and resulting in
pricing steering inaccuracies (as the overall
optimization solution did not account for competitive
discounts which were applied later) and introducing
the risk of human errors. The process, which relied on
web scraping tools such as Selenium and Scrapy, was
labor-intensive and limited responsiveness to market
changes. The new competitive discount aware system
can take into account the discounts of market
competitors to ensure an attractive proposition for the
company’s customers relative to the competition
when outputting optimal final discounts. Without
awareness of these discounts, pricing steering
accuracy is negatively affected because the
optimization system cannot account for their
contribution to the total sales discount rate.
Automation increased the speed of data updates,
ensured high calculation accuracy, integrated analysis
results into pricing management, and what's most
important - ensured the pricing steering accuracy. The
system collects up-to-date information, performs
calculations, and incorporates the results into the
company’s str
ategy. A user-friendly interface simplified
the pricing steering process and reduced time spent on
operational tasks.
The iterative solution of the Lagrangian optimization
problem enables accurate calculations while accounting
for business constraints embedded in pricing policies.
This approach eliminates the influence of human error,
guarantees decision reliability, and allows the
identification of optimal discount parameters. The
combination of analytical capabilities with ease of use
creates a tool that meets business needs in a constantly
changing market environment.
The implementation of the automated system
addressed labor-intensive tasks, reduced risks
associated with data processing, and ensured high
process reliability. Zalando, as a case study, gained the
ability to quickly respond to market changes, minimizing
the impact of external factors. Pricing became more
Ma
in
co
m
p
o
n
e
n
ts
o
f
th
e
a
u
to
m
ated
in
fo
rm
at
io
n
s
y
ste
m
o
n
co
m
p
eti
ti
v
e
d
is
co
u
n
ts
Data Extraction Module
Information storage
Analytical module
User Interface
The American Journal of Engineering and Technology
103
https://www.theamericanjournals.com/index.php/tajet
The American Journal of Engineering and Technology
manageable, freeing employees to focus on other
strategic tasks.
The project resulted in reduced time and financial
costs, improved process accuracy, and simplified
pricing management. The new solution demonstrated
how automation can transform traditional approaches,
enhancing their effectiveness and adaptability to
current conditions [11,12]. Table 2 outlines the
advantages and disadvantages of using automated
competitor discount information systems.
Table 2. Advantages and disadvantages of using automated competitive
discounts information systems (compiled by the author)
Advantages
Disadvantages
Time and resource savings: eliminates manual
extraction and loading, enabling a focus on
strategic tasks.
High implementation costs: initial setup and
system acquisition may be expensive.
Data accuracy: minimizes human error in data
collection and processing.
Requires integration: integration with existing
company IT systems may be complex.
Pricing management accuracy: ensures sales
discount rate targets are accurately met
Accuracy limitations: insufficient data coverage
or restricted access to competitor pricing.
Real-time updates: enables immediate access to
competitor discount changes.
Need for staff training: requires time for
employees to learn the system's functionality.
Enhanced competitiveness: facilitates quick
responses to price changes and competitive
offers.
Dependence on data quality: inaccuracies or
errors in competitor data can distort results.
Analytics and forecasting: provides tools for
analyzing market trends.
Ethical and legal concerns: potential issues
regarding the legality of competitor data use.
Flexibility: can be customized to specific
business needs.
Scalability: easily adapts to both large and small
businesses.
Reduced operational costs: automation reduces
labor expenses.
Automated
systems
designed
for
analyzing
competitors’ pricing strategies are utilized to optimize
commercial activities under heightened market
competition. Developing such solutions involves
leveraging advanced technologies, detailed data
processing, and designing architectures that ensure
high operational accuracy and reliability.
CONCLUSION
The automated competitive discounts information
system (ACDIS) has proven effective in addressing
tasks related to optimizing pricing steering accuracy
and monitoring pricing strategies. The system's
foundation comprises web scraping methods, text
information processing algorithms, and analytical
technologies. These components have reduced time
costs, simplified processes, enhanced analysis accuracy,
and integrated data into strategic pricing management.
ACDIS has demonstrated its practical relevance by
processing large datasets from various sources while
eliminating errors associated with manual collection.
The implementation of a microservice architecture and
the integration of modern computational solutions have
enabled the system to adapt to changing market
conditions and address the specific needs of e-
commerce.
The American Journal of Engineering and Technology
104
https://www.theamericanjournals.com/index.php/tajet
The American Journal of Engineering and Technology
The findings of this study highlight the potential of
automated approaches in pricing management,
providing competitive advantages. The developed
system is suitable for use across various e-commerce
segments. Its capabilities encompass data analysis and
the optimization of business processes. Future
development directions include improving predictive
models and incorporating recommendation solutions,
which will expand the application of automated
methods.
REFERENCES
Zhang H. et al. A personalized automated bidding
framework for fairness-aware online advertising
//Proceedings of the 29th ACM SIGKDD Conference on
Knowledge Discovery and Data Mining.
–
2023.
–
pp.
5544-5553.
Brown Z. Y., MacKay A. Competition in pricing
algorithms
//American
Economic
Journal:
Microeconomics.
–
2023.
–
Vol. 15 (2).
–
pp. 109-156.
Wen C. et al. A cooperative-competitive multi-agent
framework for auto-bidding in online advertising
//Proceedings of the Fifteenth ACM International
Conference on Web Search and Data Mining.
–
2022.
–
pp. 1129-1139.
Javed M. A. et al. Design and Implementation of
Enterprise Office Automation System Based on Web
Service Framework & Data Mining Techniques
//Journal of Data Analysis and Information Processing.
–
2024.
–
Vol. 12 (4). - pp. 523-543.
Xing Y. et al. Truthful auctions for automated bidding
in online advertising // Proceedings of the Thirty-
second International Joint Conference on Artificial
Intelligence Main Track.- 2023.- pp. 2915-2922.
Xue S., Li X. Y. Competitive Online Truthful Time-
Sensitive-Valued Data Auction //arXiv preprint
arXiv:2210.10945.
–
2022. - pp. 1-32.
James N. et al. Automated checkout for stores: A
computer vision approach //REVISTA GEINTEC-
GESTAO INOVACAO E TECNOLOGIAS.
–
2021.
–
Vol. 11
(3).
–
pp. 1830-1841.
Ajiteru S. O., Iromini N. A., Oluwasogo S. A. Design and
implementation of automated pricing system using
PHP & MYSQL design and implementation of
automated pricing system using PHP & MYSQL //
Scientific Research Journal.
–
2020.
–
Vol.8. (3)
–
pp.49-
55.
Karlsson N., Sang Q. Adaptive bid shading optimization
of first-price ad inventory // 2021 American Control
Conference (ACC).
–
IEEE. - 2021.
–
pp. 4971-4978.
Arshdeep Singh Sachdeva, Shreya Kapoor et al.
Automated e-commerce and Web automation using
Puppeteer // International Journal for Modern Trends in
Science and Technology. - 2020.
–
№ 6 (12). –
pp. 277-
281.
Marchand
A.,
Marx
P.
Automated
product
recommendations with preference-based explanations
// Journal of retailing. Vol. 96 (3).
–
pp. 328-343.
Bodak B. V., Doroshenko
А. Y. Automation in e
-
procurement system with auction module // Problems
in programming.
–
2023.-
№. 2. –
pp. 91-100.
