NECCO is a Team of Social Entrepreneurs relentlessly applying business principles to solve social problems.
For 20 years and counting NECCO has built over 25,000 families and supported over 5,000 adoptions with one mission in mind: building families. To that end, NECCO decided to strategically focus on gathering and analyzing data. This data analysis, supported by evidence-based research, improves the placement of foster children as well as the recruitment, training, and retention of foster parents. By employing a strategy of “Measure, Learn, Execute, and Repeat,” NECCO has remained laser-focused on achieving the best possible outcome for children and families.
NECCO jumped at the opportunity to use their data superpowers to help.
NECCO listened to their data analysis and knew they would be able to better combat the increasing deficit between children in need and available homes. Even considering their experience using data to produce measurable results, the NECCO team found ways to:
- — Use predictive analysis to solve social problems
- — Locate and understand the insights and actions hidden in their data
- — Educate the whole organization on using those insights
- — Move forward without an on-staff data scientist
NECCO realized they did not possess the machine learning prowess necessary to use predictive analytics to improve their recruitment of foster homes for the thousands of children in need.
Realizing that machine learning education was was the way forward, NECCO activated the DataRobot signal.
Considering NECCO’s relatively small analytics team and lack of on-staff data scientists, DataRobot University (DRU) was a clear path forward for NECCO to learn how to mine their data to further improve recruitment, training, and retention of foster homes.
After attending DRU, JP from NECCO was ready to take full advantage of the DataRobot platform and start building their own solutions.
With DataRobot at their disposal, NECCO advanced their data visualization capabilities to building their own highly accurate predictive models on the DataRobot Cloud platform powered by Amazon Web Services. Equipped with the necessary knowledge and skills, NECCO was able to create models that provide better insights into the characteristics of what makes a quality foster home.
Without altering NECCO’s organizational DNA, DataRobot has already assisted them in achieving superhuman results:
|Traits & Capabilities|
|Traits & Capabilities||Data Scientist Mortal||Data Scientist Superhero|
|Bottom Line Business Impact|
|Bottom Line Business Impact||$100K+ per year||$M's+ / Year|
|Model Engine Tested|
|Model Engine Tested||No||200,000,000+ times|
|Standardization||When there's time||Every time|
|Multitasking||Single model||Multiple models|
|Package installation and dependency management|
|Package installation and dependency management||Manual||Not needed|
|Risk of coding errors|
|Risk of coding errors||Substantial||None|
|Popularity with business users|
|Popularity with business users||Somewhat||Very|
|Business user engagement|
|Business user engagement||Too busy||Always available|
|Helped with guardrails|
|Helped with guardrails||None||Yes|
|Skills Needed||Significant - PhD-level||PhD not required|
|Model deployment effort|
|Model deployment effort||Significant||Effortless|
|Model iteration||Manual & slow||Automated|
|Helped by other Data Scientists|
|Helped by other Data Scientists||No||85+|
|Algorithms and libraries|
|Algorithms and libraries||A comfortable few||Many|
|Number of models / month|
|Number of models / month||Very Few||Thousands|
|Model Transparency||None||X-Ray Vision|
|Explainable Models||'Black Box'||Automatic|
To be continued…
This is not the end of the alliance between NECCO and DataRobot. Although NECCO already sees a noticeable increase in its success rate, they plan to use DataRobot to further analyze their historical and future data to continuously learn and improve. Additionally, now that they are familiar with the powers of DataRobot, they plan to use the platform to help even more families by increasing success rates and predicting what types of support will be most effective for each individual child and family.
“There is such a large gap between the number of children that need caring homes and the number of available families. DataRobot gives us the ability to use the data at our disposal to close that gap, which will build families better.”