Monnai GigScore
Integrating gig workers into credit platforms promotes inclusivity by utilising alternative and non-traditional data sources.
Created on 4th November 2024
•
Monnai GigScore
Integrating gig workers into credit platforms promotes inclusivity by utilising alternative and non-traditional data sources.
The problem Monnai GigScore solves
The gig economy is projected to grow by 30-50 million workers by 2030, with around 70% of them relying on informal loans from friends, family, or unregulated sources. This often results in exorbitant interest rates, limited credit access, high collateral requirements, and an overall unsafe borrowing process.
Currently, gig workers face significant challenges when trying to onboard to formal credit platforms
- Inconsistency: Fluctuating earnings and unstable job situations make it difficult to accurately assess creditworthiness
- Limited History: Many gig workers are new to the workforce and lack a formal credit history
- High Interest Rates: They often face higher interest rates due to the perceived risk associated with their income instability
- Limited Financial Products: Traditional financial institutions do not offer products tailored to the unique needs of gig workers
- Unfavorable Debt-to-Income Ratios: Inconsistent income can lead to unfavorable ratios, complicating loan approvals further
- Regulatory Barriers: Lack of understanding of the gig economy among lenders can result in policies that inadvertently exclude gig workers
- Limited Documentation: Many gig workers operate in informal sectors, lacking the necessary documentation to support their credit applications
We aim to leverage alternative data to integrate gig workers into formal credit platforms by developing a specialized credit score tailored to their unique circumstances.
Our approach focuses on three areas:
-
Reputation: Analyze behavioral data to assess trustworthiness. Utilize digital footprints to establish identity and credibility for those with limited identification
-
Financial Insights: Evaluate past, current, and projected financial health to gauge creditworthiness. Predict income stability and identify income sources
-
Asset and Liability Assessment: Understand the gig worker's financial landscape by evaluating assets and liabilities, ensuring a comprehensive view.
Challenges we ran into
-Limited Data for Gig Workers: Traditional data sources have minimal information on gig workers, making credit assessments difficult. We addressed this by integrating data from gig apps to better capture earnings and work patterns, creating a more comprehensive credit profile
-Efficient Consent Management: Data sources require separate customer consent, impacting user experience. While more data helps improve scoring, we limited our requests to high-impact sources, minimizing disruption and enhancing user satisfaction
-Ensuring Data Reliability: Gig work’s unstable nature means data can be inconsistent and hard to verify. We tackled this by validating information across sources, including cash flow proxies and app data, which helped us build a reliable profile.
-Alternative to Bank Statements: Gig workers often lack traditional financial records. To address this, we used gig app statements to track income stability, serving as a proxy for conventional bank statements
-Fraud Detection: Preventing fraud requires integrating multiple non-traditional sources. We correlated data like telecom account longevity and e-commerce activity with standard sources, helping us detect potential fraud.
-Minimal Digital Presence: Many gig workers have limited digital profiles. We focused on a few major platforms for data collection, gaining insights that strengthen our scoring algorithm
-Adapting Underwriting Models: Traditional models aren’t suited for gig workers' variable incomes. Data from gig apps and digital footprints, we adapted our models to better reflect gig workers’ financial patterns
-Setting Risk Thresholds: Finding balanced risk thresholds was challenging. We refined our scoring parameters to ensure fair risk assessments, capturing the unique financial stability of gig workers
-Score Interpretability: Our multi-source model could complicate the score, impacting trust. We prioritized transparency, breaking down how each data point influences the score.
Tracks Applied (1)