Beginning in 2013, MobiDev has transformed Comcash from a locally-based POS solution to a complex cloud-based retail ERP system with advanced data science capabilities. Today, we continue to support Comcash development, ensuring the platform operates flawlessly in over 3,000 locations and integrates seamlessly with diverse custom hardware.
Country
USA
Industry
Retail
Cooperation period
2013-current
Cooperation type
Dedicated development team of 6-8 experts
Country
USA
Industry
Retail
Cooperation period
2013-current
Cooperation type
Dedicated development team of 6-8 experts
[Together with MobiDev], we’re able to work on a 24-hour development cycle, and we release software repeatedly faster than any of our competitors — and there is no overtime. We could never create what we have with MobiDev in my office in California. The tech market is just too competitive these days. If you are interested in developing a world-class product and working with a great group of friendly co-workers every day, I wholeheartedly recommend MobiDev.
Since 2013, MobiDev has provided comprehensive support for the entire development process of the Comcash system, ensuring its ongoing deployment and evolution. Over the years, Comcash has undergone a full modernization, transitioning into a cloud-based solution and enhancing its functionality with data science capabilities. The increasing popularity of Comcash led to its acquisition by POS Nation in October 2022. Today, Comcash boasts a presence in over 3,000 locations and seamlessly integrates with a wide range of custom hardware, including printers, scanners, scales, signature capture terminals, as well as EMV and NFC payment terminals.
Reflecting on the late 20th century, the digitization of the retail industry experienced significant advancements and growth. Comcash entered the market in 1996, offering a locally-based POS solution for US retail stores. As technology rapidly evolved in the subsequent years, Richard considered the perspective of transforming Comcash from on-premise to cloud-based systems, thereby creating more robust and innovative products for his clients.
In 2013, Comcash CEO Richard Stack committed MobiDev to completely revamping Comcash, transforming it into a sophisticated cloud-based retail ERP system with advanced sales prediction capabilities.
In the realm of serving the retail industry, modern software is required to provide continuous operation, robust inventory management and planning functionality, scalability, and comprehensive coverage of omnichannel operations. Retailers often seek to grow their chains by opening new locations and aim to operate both online and offline 24/7, regardless of internet connection. They require a comprehensive set of tools to optimize procurement and maintain a balance between demand and available inventory.
During the initial year of cooperation, the dedicated development team successfully launched the first iteration of Comcash, aimed at replacing the older version of the product. Beginning with comprehensive consulting, we crafted project documentation that clarified the requirements, mitigated risks, and prioritized the desired scope for the first version of the app.
After finalizing the optimal roadmap, the MobiDev team managed the entire development cycle of Comcash, including app design. The system was deployed in mid-2014 for its first retail chain. Since then, MobiDev has continuously enhanced Comcash, with a team size ranging from 6 to 8 members, implementing sales prediction models to offer clients the added advantage of optimizing purchasing strategies.
To meet the demand for 24/7 failsafe service, MobiDev implemented an ecosystem enabling instant updates for all POS terminals with a simple button push. Additionally, the support team can set up a new instance in just ten to fifteen minutes.
Another significant advancement involved the automation of testing to enhance stability, decrease minor updates, and expedite regular major releases while maintaining product quality. Leveraging a standard internal API, automated testing runs, and basic scenarios led to a reduction in regression testing time from one week to two days.
MobiDev team implemented an adaptive selective model that forecasts demand for the upcoming weeks, based on users’ retail sales data. Processing this data to identify high-demand items was crucial, utilizing several autoregressive models with external data inputs. A key feature of this model is its adaptability, allowing forecasting for specific products at any given time.
Utilizing DS/ML libraries and methodologies such as Pandas and ABC-XYZ analysis, a statistical report was generated to categorize products based on popularity and revenue. This data on most and least profitable items is utilized for targeted discount strategies, ultimately boosting retail sales.
Additionally, a third model, leveraging Mlxtend, Pandas, associative rules, and the Apriori algorithm, was integrated to suggest relevant complementary products often purchased together with selected items. This assists in recommending additional products to enhance each customer’s shopping experience and drive additional revenue.
Webinar|AI and Tech in Retail & Hospitality
