Lessons in Big Data InfoAg Conference July 18, 2018 M A I N S T R E - - PowerPoint PPT Presentation

M A I N S T R E E T D ATA . C O

Lessons in Big Data

InfoAg Conference July 18, 2018

INNOVATE VALIDATE INNOVATE VALIDATE

W H O I S M A I N S T R E E T D ATA

• Strong advocate for data analytics in agriculture
• Independent
• Credible
• Collaborative
• Pro-Partnering

A P O W E R F U L PA R T N E R S H I P

T H E K E Y T O A C C E L E R AT I N G A D O P T I O N I S VA L I D AT I O N A N D T H E K E Y T O VA L I D AT I O N I S B E N C H M A R K I N G

The Most Accurate and Objective Primary Data Set

1 BILLION UNIQUE MICROFIELDS SCOPE SCALE QUALITY 1.3B

5,100 10,000 Leading Agribusinesses

TEST PLOTS

Main Street Data

S E V E N + Y E A R H E A D S TA R T C R E AT I N G T H E L A R G E S T S O U R C E O F C L E A N “ G R O U N D T R U T H ” Y I E L D D ATA I N T H E U . S .

T H E H I G H E S T Q U A L I T Y Y I E L D D ATA S E T PROPRIETARY DATA COLLECTED FROM MANAGED COMBINE FLEET

• Proprietary Fleet of over 300 Combines

Rotating to ~ 800 Customers per year in 26 States

• More than 7 Years of Data Collected, Using

Verizon’s Data Network

• Focused on Corn, Wheat, and Soybean

Crops

• This method of highly controlled data

collection at scale will not be replicated

T H E M A G N I T U D E O F O U R Y I E L D D ATA B A S E I S VA S T A N D C O L L E C T E D I N R E A L - T I M E

Over 7 million acres of real-time yield results from a managed fleet of

• ver 300 combines

which Is 1.3 billion unique micro-fields that passed quality assurance

30 ft. 5 ft.

1.3 billion unique micro-fields yield, weather, soil and topography which Are used to create the MSD yield benchmarks & Validator Data captured every second which Is every 150 square feet of a field Every yield

• bservation is

validated and calibrated which Makes the MSD yield database the largest and most accurate yield database available

U N M AT C H E D Y I E L D D ATA P R O C E S S D E L I V E R S D I F F E R E N T I AT E D M O D E L Q U A L I T Y Y I E L D D ATA + A B I L I T Y T O I N J E S T A N D C L E A N N E W D ATA S E T S

Unmanaged Data Collection vs. Managed Data Collection Random Combines

Difficult to Get Farmers to Provide Data, No Control Over Equipment Condition or Maintenance

MACHINERY Managed Fleet

Highly Controlled Logistical Operation, Including Inspection and Adjustment of Key Equipment Components

Manual

Complicated, Manual Process That Is Prone to Setting Errors

CALIBRATION and PREPARATION Precise

Processes to Correct for Unplanned Operator Adjustments and Maintain Calibration

Unsupervised

Different Manual Processes Making Consolidation Difficult and Causing Errors

DATA COLLECTION and MONITORING Supervised

Remote Monitoring of Combine Fleet and Yield Through Cell Network

None

No Way to Tell What Data Is Corrupted

• vs. What Is Valid

QA and VALIDATION Rigorous

Industry Leading Control of Data Quality Assurance

T H E M A I N S T R E E T D ATA P R O P R I E TA RY A N A LY T I C S P L AT F O R M I S B U I LT O N F O U N D AT I O N A L D ATA A N D S C I E N C E , A N D I S S C A L A B L E I N T O T H E F U T U R E

PUBLIC DATA

(20 Yr. History, Daily 10-Day Forecasts) (Drought Monitor, Crop Progress) (20 Year Moisture Index) (Soil Index) (Precipitation, Temperature, Growing Days)

UNIQUE MICRO-FIELD (150ft2) SIGNATURES BILLIONS of DATA ELEMENTS HYBRID REGRESSION MODELS

Proprietary Soil Index Proprietary Harvest Index Proprietary Field Index

PROPRIETARY YIELD DATABASE

Yield Data Captured from Managed FleeT YIELD PATTERN IDENTIFICATION Proprietary methodology builds meaningful environmental and climatological layers, which are paired with yield data to understand yield

• utcomes

YIELD DATA ANALYSIS Data science engine analyzes 1 billion unique micro fields of data to develop yield benchmark (New Yield + Farming Practice Data)

COOP DATA

M A I N S T R E E T + G I S C E X PA N D & E N H A N C E R I C H D ATA & R E A L S O L U T I O N S

Main Street Yield Database: Yield data captured from managed fleet Main Street Field Database: Proprietary analysis and methodology used to build environmental and climatological layers, which are paired with yield data to create unique Field Database GISC Data: Data collected through GISC members will provide rich source of not only yield data but also on farming inputs and practices that will allow MSD and GISC to expand and enhance benchmarking and validation into the future. Main Street Yield Benchmark: Data scientists analyze 1.3 billion unique micro-fields of data to develop yield benchmark Future Foundation

C O M I N G S O O N : M A R K E T V I S I O N C U S T O M I Z E D A N A LY T I C S F O R L O C A L G R A I N M A R K E T I N G

• Easy-to-use analytics tool

that informs management and grain marketing decisions to increase profit potential real-time

• Sold to Growers, Land

Owners and AgriBusiness

VA L I D AT O R I S L I V E S T O P B Y B O O T H 1 5 6 F O R A D E M O

Thank you

RON LEMAY CEO MAIN STREET DATA

15