hunchlab 2.0 predictive missions: under the hood
DESCRIPTION
TRANSCRIPT
![Page 1: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/1.jpg)
340 N 12th St, Suite 402 Philadelphia, PA 19107
215.925.2600 [email protected]
www.hunchlab.com
Missions: Under the Hood
![Page 2: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/2.jpg)
Amelia Longo Business Development Associate [email protected] 215.701.7715
Jeremy Heffner HunchLab Product Manager [email protected] 215.701.7712
![Page 3: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/3.jpg)
Places
People
Patterns } Prioritization
![Page 4: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/4.jpg)
Predictive Missions
![Page 5: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/5.jpg)
It’s the fourth Tuesday in January and school is in session. There were 3 burglaries and 2 robberies yesterday. Six bars, three take-out stores, and a school are in the neighborhood. The forecast is 17° with cloudy skies. Where do you focus your 2 vehicles?
![Page 6: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/6.jpg)
![Page 7: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/7.jpg)
![Page 8: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/8.jpg)
![Page 9: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/9.jpg)
![Page 10: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/10.jpg)
![Page 11: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/11.jpg)
How would you do it?
![Page 12: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/12.jpg)
![Page 13: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/13.jpg)
Analyst Process
• Identify relevant factors – Training / Literature – Experience
• Use heuristics – high concentration of past crime è higher risk – near a bar on a Friday night è higher risk – near the police station è lower risk – concentration of ex-offenders è higher risk – near transit stops è higher risk
![Page 14: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/14.jpg)
![Page 15: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/15.jpg)
![Page 16: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/16.jpg)
![Page 17: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/17.jpg)
![Page 18: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/18.jpg)
?
![Page 19: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/19.jpg)
How HunchLab Works
![Page 20: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/20.jpg)
A computer system designed to learn how to accomplish a task by using historic data sets. There are different ways (algorithms) to accomplish this training process.
term: machine learning
![Page 21: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/21.jpg)
The step-by-step procedure to accomplish a given calculation. Different algorithms have different qualities. Algorithms are used to train a machine learning model.
term: algorithm
![Page 22: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/22.jpg)
Overall Process
1. Generate training examples of outcomes
2. Enrich with relevant variables
3. Build models
4. Evaluate accuracy
5. Select best performing model
![Page 23: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/23.jpg)
Generate Examples
![Page 24: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/24.jpg)
~ 500 ft cells & 1+ hour time slices
![Page 25: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/25.jpg)
Data Volume
• Space – Lincoln, NE is 90 sq miles – 500 ft cell size creates 12,000 cells
• Time – 3 years of data – 1 hour resolution – 26,000 hour blocks
• Space x Time – 312,000,000 hour block cells (examples)
![Page 26: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/26.jpg)
Data Volume
• Space – Lincoln, NE is 90 sq miles – 500 ft cell size creates 12,000 cells
• Time – 3 years of data – 1 hour resolution – 26,000 hour blocks
• Space x Time – 312,000,000 hour block cells (examples)
• Sampling FTW! – Outcomes are sparse (small % of examples have crimes) – Sampling strategy preserves crime events
![Page 27: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/27.jpg)
Representing Crime Theories
![Page 28: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/28.jpg)
![Page 29: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/29.jpg)
• Crime predictions based on: – Baseline crime levels
• Similar to traditional hotspot maps
– Near repeat patterns • Event recency (contagion)
– Risk Terrain Modeling • Proximity and density of geographic features • Points, Lines, Polygons (bars, bus stops, etc.)
– Collective Efficacy • Socioeconomic indicators (poverty, unemployment, etc.)
Predictive Missions
![Page 30: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/30.jpg)
• Crime predictions based on: – Routine Activity Theory
• Offender: proximity and concentration of known offenders • Guardianship: police presence (AVL / GPS) • Targets: measures of exposure (population, parcels, vehicles)
– Temporal cycles • Seasonality, time of month, day of week, time of day
– Recurring temporal events • Holidays, sporting events, etc.
– Weather • Temperature, precipitation
Predictive Missions
![Page 31: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/31.jpg)
Representing Crime Theories Risk Terrain Modeling
![Page 32: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/32.jpg)
Gun shoo)ngs example Source: Rutgers, h8p://www.rutgerscps.org/rtm/irvrtmgoogearth.htm
![Page 33: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/33.jpg)
![Page 34: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/34.jpg)
![Page 35: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/35.jpg)
![Page 36: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/36.jpg)
![Page 37: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/37.jpg)
![Page 38: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/38.jpg)
![Page 39: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/39.jpg)
![Page 40: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/40.jpg)
crimes prior7 prior364 dayssincelast bardist dow
0 0 0 365 >2000ft Monday
0 0 1 234 >2000ft Monday
1 1 3 3 750ft Tuesday
0 0 2 43 500ft Wednesday
2 0 2 74 500ft Friday
![Page 41: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/41.jpg)
Representing Crime Theories Aoristic Analysis
![Page 42: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/42.jpg)
crimes probability
0 0
1 a
2 b
3 c
4 d
![Page 43: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/43.jpg)
crimes weights prior7 prior364 dayssincelast bardist dow
0 1 0 0 365 >2000ft Monday
0 1 0 1 234 >2000ft Monday
0 0.5 1 3 3 750ft Tuesday
1 0.5 1 3 3 750ft Tuesday
0 0 0 2 43 500ft Wednesday
0 0.13 0 2 74 500ft Friday
1 0.32 0 2 74 500ft Friday
2 0.55 0 2 74 500ft Friday
![Page 44: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/44.jpg)
Building Models
![Page 45: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/45.jpg)
Models
• Baseline – Baseline models (6)
• Counts – 28 day – 56 day – 364 day
• Kernel Densities – 28 day – 56 day – 364 day
– HunchLab models • Variations of a stacked ensemble:
– examples è gradient boosting machine (gbm) è y/n probabilities
– y/n probabilities è generalized additive model (gam) è counts
![Page 46: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/46.jpg)
A machine learning algorithm that recursively partitions a data set based upon variable values forming a tree-like structure.
term: decision tree
![Page 47: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/47.jpg)
crimes prior7 prior364 dayssincelast bardist dow
0 0 0 365 >2000ft Monday
0 0 1 234 >2000ft Monday
1 1 3 3 750ft Tuesday
0 0 2 43 500ft Wednesday
2 0 2 74 500ft Friday
![Page 48: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/48.jpg)
A machine learning algorithm that uses a series of weaker models (typically decision trees) that are trained upon the residuals of prior iterations (boosting) to form one stronger model.
term: gradient boosting machine (GBM)
Build Decision Tree 1
Predict with 1
Calculate errors
1 Build Decision Tree 2
Predict with 1 & 2
Calculate errors
2 Build Decision Tree 3
Predict with 1-3
Calculate errors
3 …
![Page 49: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/49.jpg)
A regression model that fits smoothed functions to the input variables. Compare to a generalized linear model which fits just a single coefficient to each variable.
term: generalized additive model (GAM)
![Page 50: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/50.jpg)
HunchLab Model Building
1. Build a GBM – examples è gradient boosting machine è y/n probabilities
![Page 51: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/51.jpg)
312 million
4 million
1 mil 1 mil 1 mil 1 mil
Sampling
4 folds
GBM
}
1 mil
Evaluate
43
200
![Page 52: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/52.jpg)
312 million
4 million
Sampling
GBM 43
![Page 53: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/53.jpg)
HunchLab Model Building
1. Build a GBM – examples è gradient boosting machine è y/n probabilities
• Segment examples into several folds – For each fold build a GBM model on the rest of the data – For each iteration in the GBMs:
» Randomly sample a portion of the data (stochastic) » Adjust weights of observations (adaptive boosting)
• Determine how many iterations result in the most accurate model • Build a GBM on all of the data for that many iterations
![Page 54: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/54.jpg)
![Page 55: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/55.jpg)
HunchLab Model Building
2. Build a GAM – y/n probabilities è generalized additive model è counts
• Transforms (“bends”) GBM output into counts • Calibrates count levels with other key variables
![Page 56: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/56.jpg)
![Page 57: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/57.jpg)
Example
![Page 58: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/58.jpg)
Lincoln NE
![Page 59: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/59.jpg)
Lincoln Assaults
![Page 60: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/60.jpg)
Lincoln Assaults
![Page 61: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/61.jpg)
Lincoln Assaults
![Page 62: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/62.jpg)
Lincoln Assaults
![Page 63: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/63.jpg)
Lincoln Assaults
![Page 64: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/64.jpg)
Selecting Models
![Page 65: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/65.jpg)
Selecting Models
1. Build models holding out last 28 days of data
2. Score each model
– Combine different metrics into a selection score
3. Select best score
4. Rebuild the best model (including last 28 days data)
![Page 66: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/66.jpg)
Cells ranked highest to lowest
A map represented as a grid of cells
0% 100%
Crime Location
![Page 67: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/67.jpg)
Cells ranked highest to lowest
0% 100%
Percent of Patrol Area to Capture All Crimes
Average Crime Rank
0%
50%
100%
0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
Percent of Crimes Captured vs. Percent of Patrol Area
![Page 68: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/68.jpg)
0% 20% 40% 60% 80% 100%
Assault
Burglary
MVT
Ra
pe
Robb
ery
Percent of Patrol Area to Capture All Crimes
![Page 69: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/69.jpg)
0
0.1
0.2
0.3
0.4
0.5
0.6
Assault Burglary MVT Rape Robbery
Average Crime Rank
![Page 70: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/70.jpg)
0
0.2
0.4
0 0.02 0.04 0.06 0.08 0.1 0.12 0.14 0.16
Perc
ent
of C
rime
s C
ap
ture
d
Percent of Land Area
Theft of Motor Vehicle
![Page 71: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/71.jpg)
Overall Process
1. Generate training examples of outcomes
2. Enrich with relevant variables
3. Build models
4. Evaluate accuracy
5. Select best performing model
![Page 72: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/72.jpg)
Our Solution • Learns from several years of your data
• Automatically determines which theories apply
– more than just crime data
• Prevents over-fitting
• Calibrates predictions
• Selects a model based upon a blind evaluation
– prioritization and count-based metrics
![Page 73: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/73.jpg)
Our Solution • Learns from several years of your data
• Automatically determines which theories apply
– more than just crime data
• Prevents over-fitting
• Calibrates predictions
• Selects a model based upon a blind evaluation
– prioritization and count-based metrics
• But it still cannot make your morning coffee
![Page 74: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/74.jpg)
Additional Information • How did HunchLab originate?
• How does HunchLab represent crime theories?
• What data is needed?
• How does the modeling work specifically?
![Page 75: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/75.jpg)
Questions
340 N 12th St, Suite 402 Philadelphia, PA 19107
215.925.2600 [email protected]
www.hunchlab.com
![Page 76: HunchLab 2.0 Predictive Missions: Under the Hood](https://reader033.vdocuments.us/reader033/viewer/2022051313/54b3a8664a79599c5c8b4794/html5/thumbnails/76.jpg)
340 N 12th St, Suite 402 Philadelphia, PA 19107
215.925.2600 [email protected]
www.hunchlab.com
Amelia Longo Business Development Associate [email protected] 215.701.7715
Jeremy Heffner HunchLab Product Manager [email protected] 215.701.7712