Hugosave - 173tech

Customer Behaviour

Activity based segmentation for this investment app

Objective

Identify and interpret irregular investor behaviours by modelling their transaction patterns.

Obstacle

The absence of a modern analytics infrastructure to support detailed behavioural analysis.

Outcome

A scalable data platform enabling activity-based segmentation and automated behavioural alerts.

Background

Hugosave is a digital financial companion designed to empower people of all generations to spend, save, and invest with confidence and ease. Recognising the limitations of their existing tools, they turned to 173tech to establish a robust and scalable data infrastructure that would serve as the backbone of their analytics-driven approach. As a startup, they knew that unlocking the power of app usage analytics would be critical to driving their growth, and were looking for a cost-effective and quick way of getting started with data.

Challenges

Impartial Expertise: Although Hugosave had some familiarity with data tools, they were concerned that internal biases, shaped by past experiences, might influence their choices. They needed a partner with extensive experience across a wide range of tools who could provide objective, well-rounded advice.

Uncovering Key Trends: Hugosave was dealing with a vast volume of transactional data, making it difficult to pinpoint meaningful trends that could guide product improvements. While they had visibility into general activity levels, they lacked a clear understanding of how these activities translated to customer value or impacted retention rates.

Solution

Infrastructure: We designed Hugosave’s data stack with scalability and cost-efficiency at its core. By carefully structuring how data was collected and stored, we enabled Hugosave to analyse large volumes of transactions without incurring runaway costs. This foundation provided visibility into critical metrics, including investments held, log-ins, user queries, and customer lifetime value.

Activating Data: Once the infrastructure was in place, we focused on usability. Through Metabase, we built intuitive dashboards that gave Hugosave a clear view of their operations, underpinned by core data models such as customer lifecycle tracking, transaction cohorts, and engagement funnels. These models connected app activity with financial outcomes and enabled automated segmentation flags, such as identifying when high-value users deviated from expected investment cycles. To drive responsiveness, we implemented real-time Slack alerts, ensuring the team could act quickly when key behaviours shifted.

Impact

Usage Patterns: Unlike many consumer apps, Hugosave’s users engaged sporadically, often tied to investment cycles, which made traditional engagement and churn metrics less meaningful. To address this, we modelled activity patterns around key financial events rather than daily usage, identifying behaviours such as pre-investment research, periodic log-ins, and recurring transaction triggers. By reframing metrics to reflect these irregular cycles, we were able to surface meaningful signals of customer health and create a foundation for more accurate segmentation and proactive interventions.

Segmenting User Behavior: To address this, we conducted an in-depth analysis of their transactional data to segment users based on their activity patterns. This allowed us to define typical behaviours for each group. For example, one segment consisted of users who managed their investments annually. By identifying the lead-up behaviours, such as researching options in advance, we were able to detect when these activities were missing and set up automated flags.