Florida crash prediction system

To Whom It May Concern:

Pursuant to the Florida Sunshine Law, I hereby request the following records:

1) All technical manuals, guides, handbooks, instructions, and department policies provided to Florida Highway Patrol staff regarding proper use of the crash prediction model created for FLHSMV by Urban SDK. Please note: FLHSMV has previously provided me with its memorandum of understanding with Urban SDK for this predictive model in response to an earlier public records request (see attached).

2) All validation test results for the crash prediction model since the contract with Urban SDK began. This should include analyses of the model's accuracy (such as AUC or false/true positives) conducted by FLHSMV or provided to the department by Urban SDK or third parties.

3) The data dictionary/library for the FLHSMV's crash analytics model developed by Urban SDK. To clarify: A data dictionary/library is a document that lists and defines the different fields in a dataset, it does not contain the actual data.

4) Crash prediction data generated by FLHMSV's predictive model from Jan. 1, 2020 until the date this request is processed. This data should be provided in .csv, .xls, or equivalent format and include the geolocation/address of predicted crashes and the input data used to make those predictions. Please note: FLHMSV has previously provided me with the daily emails containing crash prediction data that Urban SDK's system sends to department staff. In this request, I am asking for the underlying data used to generate those reports.

I ask that all fees be waived as I am a journalist and intend to use the requested records to publish articles in the public interest about the operations of a government agency. In the event you choose to impose fees, I request a detailed breakdown of the fees, including the hourly wage of each employee involved and an explanation of the employee hours required to fulfill the request.

Should you choose to reject this request or redact portions of responsive documents, I ask that you provide a detailed breakdown of the statutory exemptions and associated case law underlying your decision to withhold each/any portions from public review.

In the event that there are fees, I would be grateful if you would inform me of the total charges in advance of fulfilling my request. I would prefer the request filled electronically, by e-mail attachment if available or CD-ROM if not.

Thank you in advance for your anticipated cooperation in this matter. I look forward to receiving your response to this request within 10 business days.

Sincerely,

Todd Feathers

Molly,

I don't have any record of a previous response from your office stating there are no responsive records.

Could you please explain what you mean by that? Based on the contract and records the department has already provided me, it seems pretty clear that there are records responsive to this request.

Thank you,
Todd Feathers

Hello Molly,

Thank you for the response and help with this.

The documents previously provided by FDHSMV indicate that there was an agreement and that the system was implemented.

In response to an earier public records request, submitted in October 2021 and completed January 24, 2022, Jessica Kelleher from FDHSMV sent me a signed agreement (attached) between FDHSMV and Urban SDK Inc. for the crash prediction system. She also provided one year's worth of daily, automated emails (from March 27, 2020 through February 23, 2021) containing crash predictions sent by the Urban SDK system to Chief Tim Roufa.

Best,
Todd Feathers