StarZero All shows Try the podcast clipper →

Apr 6, 2017 · 24m · mad

Reengineering Urban Transit // Daniel Ramot and Saar Golde, Via (FirstMark's Data Driven)

Saar Golde · 12m spoken Daniel Ramot · 6m spoken Matt Turck · 25s spoken
0:00 / 0:00
▶ Watch on YouTube →

gold bands on the timeline = statements, start to end. Hover to read, click to jump. CC turns on captions

At a Data Driven NYC event, Via leaders Daniel Ramot and Saar Golde explain how Via uses dynamic routing algorithms, predictive driver supply forecasting, and high-occupancy shared shuttles to reengineer urban public transportation.

How this conversation actually went

Every chapter scored 0–10 on four independent dynamics. Hover any point for the reasoning behind the score. Matt holds 2.1% of the talking time here. How this is scored →

Matt as informed peer 0.4 Guest teaching 2.4 Guest disagreement 0.2 Matt pushing back 0.2
05100:0010:0020:000:09–3:08 · Matt as informed peer 0/10 Daniel Ramot on the Future of Urban Transit Daniel Ramot delivers an opening monologue presentation detailing Via's vision to build a software control layer for dynamic on-demand shuttle networks. Host Matt Turck does not participate during this presentation segment, so host scores are zero.3:08–6:11 · Matt as informed peer 0/10 Saar Golde on the Transportation Operating System Architecture Saar Golde outlines Via's operating system architecture, covering real-time routing algorithms and static pricing puzzles. As a monologue presentation section, the host remains silent.6:11–9:57 · Matt as informed peer 0/10 Driver Supply Forecasting and Behavioral Economics Saar Golde explains driver supply forecasting, futures market framing, and driver promotion response models. Host Matt Turck is absent during this monologue segment.9:57–13:06 · Matt as informed peer 0/10 Shared Ride System Efficiency and Environmental Impact Saar presents empirical data regarding passenger-mile efficiency and environmental congestion reduction relative to Uber and traditional taxis. The segment concludes the monologue presentation without host interaction.13:06–24:12 · Matt as informed peer 2/10 Panel Discussion and Audience Q&A Matt Turck asks a brief question regarding data science team size before facilitating audience Q&A on pricing strategies, geographic expansion, and behavioral economics. The overall exchange is collaborative and informative rather than contentious.0:09–3:08 · Guest teaching 2/10 Daniel Ramot on the Future of Urban Transit Daniel Ramot delivers an opening monologue presentation detailing Via's vision to build a software control layer for dynamic on-demand shuttle networks. Host Matt Turck does not participate during this presentation segment, so host scores are zero.3:08–6:11 · Guest teaching 2/10 Saar Golde on the Transportation Operating System Architecture Saar Golde outlines Via's operating system architecture, covering real-time routing algorithms and static pricing puzzles. As a monologue presentation section, the host remains silent.6:11–9:57 · Guest teaching 2/10 Driver Supply Forecasting and Behavioral Economics Saar Golde explains driver supply forecasting, futures market framing, and driver promotion response models. Host Matt Turck is absent during this monologue segment.9:57–13:06 · Guest teaching 2/10 Shared Ride System Efficiency and Environmental Impact Saar presents empirical data regarding passenger-mile efficiency and environmental congestion reduction relative to Uber and traditional taxis. The segment concludes the monologue presentation without host interaction.13:06–24:12 · Guest teaching 4/10 Panel Discussion and Audience Q&A Matt Turck asks a brief question regarding data science team size before facilitating audience Q&A on pricing strategies, geographic expansion, and behavioral economics. The overall exchange is collaborative and informative rather than contentious.0:09–3:08 · Guest disagreement 0/10 Daniel Ramot on the Future of Urban Transit Daniel Ramot delivers an opening monologue presentation detailing Via's vision to build a software control layer for dynamic on-demand shuttle networks. Host Matt Turck does not participate during this presentation segment, so host scores are zero.3:08–6:11 · Guest disagreement 0/10 Saar Golde on the Transportation Operating System Architecture Saar Golde outlines Via's operating system architecture, covering real-time routing algorithms and static pricing puzzles. As a monologue presentation section, the host remains silent.6:11–9:57 · Guest disagreement 0/10 Driver Supply Forecasting and Behavioral Economics Saar Golde explains driver supply forecasting, futures market framing, and driver promotion response models. Host Matt Turck is absent during this monologue segment.9:57–13:06 · Guest disagreement 0/10 Shared Ride System Efficiency and Environmental Impact Saar presents empirical data regarding passenger-mile efficiency and environmental congestion reduction relative to Uber and traditional taxis. The segment concludes the monologue presentation without host interaction.13:06–24:12 · Guest disagreement 1/10 Panel Discussion and Audience Q&A Matt Turck asks a brief question regarding data science team size before facilitating audience Q&A on pricing strategies, geographic expansion, and behavioral economics. The overall exchange is collaborative and informative rather than contentious.0:09–3:08 · Matt pushing back 0/10 Daniel Ramot on the Future of Urban Transit Daniel Ramot delivers an opening monologue presentation detailing Via's vision to build a software control layer for dynamic on-demand shuttle networks. Host Matt Turck does not participate during this presentation segment, so host scores are zero.3:08–6:11 · Matt pushing back 0/10 Saar Golde on the Transportation Operating System Architecture Saar Golde outlines Via's operating system architecture, covering real-time routing algorithms and static pricing puzzles. As a monologue presentation section, the host remains silent.6:11–9:57 · Matt pushing back 0/10 Driver Supply Forecasting and Behavioral Economics Saar Golde explains driver supply forecasting, futures market framing, and driver promotion response models. Host Matt Turck is absent during this monologue segment.9:57–13:06 · Matt pushing back 0/10 Shared Ride System Efficiency and Environmental Impact Saar presents empirical data regarding passenger-mile efficiency and environmental congestion reduction relative to Uber and traditional taxis. The segment concludes the monologue presentation without host interaction.13:06–24:12 · Matt pushing back 1/10 Panel Discussion and Audience Q&A Matt Turck asks a brief question regarding data science team size before facilitating audience Q&A on pricing strategies, geographic expansion, and behavioral economics. The overall exchange is collaborative and informative rather than contentious.

speaking balance: gold is Matt, purple is the guest (3 minute bins)

0:00 · Matt 0.2% · guest 99.8%0:00 · Matt 0.2% · guest 99.8%3:00 · Matt 0% · guest 100%3:00 · Matt 0% · guest 100%6:00 · Matt 0% · guest 100%6:00 · Matt 0% · guest 100%9:00 · Matt 0% · guest 100%9:00 · Matt 0% · guest 100%12:00 · Matt 6.5% · guest 93.5%12:00 · Matt 6.5% · guest 93.5%15:00 · Matt 0% · guest 100%15:00 · Matt 0% · guest 100%18:00 · Matt 3% · guest 97%18:00 · Matt 3% · guest 97%21:00 · Matt 2% · guest 98%21:00 · Matt 2% · guest 98%24:00 · Matt 100% · guest 0%24:00 · Matt 100% · guest 0%
Sharpest disagreement ▶ 23:11 Dispelling academic assumptions about individual driver pay optimization

Saar gently counters the audience question premise that companies optimize pay thresholds per individual driver, explaining that real-world driver behavior is far too complex for academic modeling assumptions.

 Hardest push from Matt ▶ 13:19 Host probing on data science organizational scale

Matt Turck steps in post-presentation to press on operational headcount, asking how large of a team is required to execute such complex calculations.

 Biggest teaching moment ▶ 20:57 Deconstructing taxi driver behavioral economics literature

Saar educates the audience on academic studies regarding NYC cab driver target earnings, explaining the practical limits of observing driver outside options in real-time.

 Matt holds his own ▶ 13:19 Host highlighting data engineering complexity

Matt Turck demonstrates technical awareness by identifying organizational capacity and data team structuring as the critical enabler for real-time routing engines.
the scores for every segment, with the reasoning behind each
ChapterTopicMatt as informed peerGuest teachingGuest disagreementMatt pushing backWhy
Daniel Ramot on the Future of Urban Transit 0200 Daniel Ramot delivers an opening monologue presentation detailing Via's vision to build a software control layer for dynamic on-demand shuttle networks. Host Matt Turck does not participate during this presentation segment, so host scores are zero.
Saar Golde on the Transportation Operating System Architecture 0200 Saar Golde outlines Via's operating system architecture, covering real-time routing algorithms and static pricing puzzles. As a monologue presentation section, the host remains silent.
Driver Supply Forecasting and Behavioral Economics 0200 Saar Golde explains driver supply forecasting, futures market framing, and driver promotion response models. Host Matt Turck is absent during this monologue segment.
Shared Ride System Efficiency and Environmental Impact 0200 Saar presents empirical data regarding passenger-mile efficiency and environmental congestion reduction relative to Uber and traditional taxis. The segment concludes the monologue presentation without host interaction.
Panel Discussion and Audience Q&A 2411 Matt Turck asks a brief question regarding data science team size before facilitating audience Q&A on pricing strategies, geographic expansion, and behavioral economics. The overall exchange is collaborative and informative rather than contentious.

Statements from this episode (11)

Prediction Not checkable as stated
Ramot: Shared, dynamic, electric, autonomous shuttles will dominate urban transit
“We believe that what we're able to now create is, is an automated control layer that will enable, ah, a whole class or a network of on-demand shuttles, and that those on-demand shuttles are going to rule the way we get around. They're going to be shared. They'…”
Daniel Ramot Apr 6, 2017 ▶ 1:07
Assertion Not checkable as stated
Ramot: Via's average wait time in New York is 5 to 6 minutes
“Our average wait times in New York are about five or six minutes.”
Daniel Ramot Apr 6, 2017 ▶ 2:07
Assertion Not checkable as stated
Ramot: Over 97% of Via rush-hour rides are shared
“Over 80% of the time during rush hours, over 97% of the time you're gonna be sharing with at least one other person, typically three, four, or more people.”
Daniel Ramot Apr 6, 2017 ▶ 2:12
Disclosure
Ramot: Via has completed 12M total rides and 250k weekly rides
“We've done over ten million rides, twelve million rides, about a quarter of a million rides a week”
Daniel Ramot Apr 6, 2017 ▶ 2:31
Disclosure
Ramot: Via licenses its transit software in Paris and England
“And we have, ah, a license, licensing deals in Paris, and England, ah, and other places around the world.”
Daniel Ramot Apr 6, 2017 ▶ 2:52
Disclosure
Golde: Via sets driver rates and promotions one day in advance
“So what we do is we set the rates and the promotions to our drivers in a way that we think will bring enough of those drivers At the right time enough of drivers of the right types the following day. So we actually commit a day in advance to prices, and then a…”
Saar Golde Apr 6, 2017 ▶ 7:00
Assertion Supported
Golde: Uber drivers average 0.6 to 0.8 empty miles per passenger mile
“We look at some of our competitors, specifically Uber, there's a paper published again, either late last year or earlier this year, showing how many miles they ride empty on average for every single passenger mile that they do, and it's about between . Six and…”
Saar Golde Apr 6, 2017 ▶ 10:53
Assertion Not checkable as stated
Golde: Via delivers two passengers per mile, outperforming competitors 3-4x
“So, on every mile we drive, we actually deliver on average two people one mile towards their destination, which is like four times better than You know, four times better than taxis, more than one in a, ah, more, more than three times better than, kind of, the…”
Saar Golde Apr 6, 2017 ▶ 12:27
Assertion Not checkable as stated
Ramot: Via drivers in New York average eight to nine hours daily
“On average, I'd say they work between in New York, sort of eight or nine hours a day.”
Daniel Ramot Apr 6, 2017 ▶ 14:53
Assertion Not checkable as stated
Ramot: Via can launch its system in a new city in an hour
“I think if we wanted to set up our system in Philadelphia, which is a test that we've run, it takes us about an hour, ah, to get it up and running.”
Daniel Ramot Apr 6, 2017 ▶ 15:36
Disclosure
Ramot: Via plans to launch premium Via Express service in coming weeks
“One of the things that we're planning to launch over the next few weeks is a service called Via Express, which will allow us to do just that, to say, when you want to pay a little bit more, there's always Via.”
Daniel Ramot Apr 6, 2017 ▶ 19:27
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 400 conversations transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.

Try the podcast clipper Learn more