Santa Barbara, California, United States
Contact Info
1K followers
500+ connections
About
Articles by Sean
Contributions
-
How can you increase client satisfaction with innovation in PM?
In my experience, fostering a culture of curiosity within a product management organization is crucial. This involves shifting the organization's mindset towards asking questions and seeking insights from customers, the market, and internal stakeholders. Rather than product managers coming to the table with preconceived notions, or their own agenda, the emphasis is on uncovering learnings and adapting strategies accordingly. It takes time, but leads to clarity, actionable metrics, and greater responsiveness to market dynamics, ultimately benefiting both customers and the organization. With this approach, you gain clarity and actionable metrics tied to specific target audiences and desired outcomes for product experiments that are measurable
-
How can you ensure statistical learning models are interpretable for business users?
Akin to the saying: "your model is only as good as the data it's trained on", the level of explainability and interpretability of the output is heavily dependent on the model(s) selected. Neural Networks are notorious for being more of a black box when it comes to explainability, whereas models constructed from Bayes' theorem, for example, tend to offer much more transparency into how the model arrived at its output. That said, there are many factors surrounding model selection that one would want to account for, including: problem domain/use-case, availability of ground truth training data, (as this determines accuracy range/model fit), requirements around explainability, and scalability (costs, re-training, reinforcement learning, etc.).
Activity
-
For my fellow programmers who use docker, I highly recommend checking out OrbStack for running and managing containers locally on MacOS. Fast…
For my fellow programmers who use docker, I highly recommend checking out OrbStack for running and managing containers locally on MacOS. Fast…
Liked by Sean Storlie
-
Often when folks talk about subject matter expertise, they’re referring to a vertical knowledge set or experience. Someone might be an expert in the…
Often when folks talk about subject matter expertise, they’re referring to a vertical knowledge set or experience. Someone might be an expert in the…
Liked by Sean Storlie
Experience & Education
Licenses & Certifications
Patents
-
Signal discovery using artificial intelligence models
Issued 11115520
Topic modeling is invaluable for organizing large volumes of communications for analysis or intervention. While numerous techniques exist for written communication, verbal exchanges pose challenges due to greater variation. Neural networks and structured machine learning struggle due to annotated training data requirements and interpretability issues. Unsupervised methods like Latent Dirichlet Allocation (LDA) are common, yet they underperform in oral communications.
Firstly, LDA treats…Topic modeling is invaluable for organizing large volumes of communications for analysis or intervention. While numerous techniques exist for written communication, verbal exchanges pose challenges due to greater variation. Neural networks and structured machine learning struggle due to annotated training data requirements and interpretability issues. Unsupervised methods like Latent Dirichlet Allocation (LDA) are common, yet they underperform in oral communications.
Firstly, LDA treats all call words equally, disregarding speaker distinctions. Varying speech patterns and word usage between parties can misidentify calls. Secondly, LDA assumes consistent language use across topics, which doesn't hold in verbal exchanges, leading to topic divergence based on locality or individual speech habits. Lastly, LDA's flat prior distribution assumes equal topic probability, disregarding real-world frequency variations. Enhanced AI models are needed for accurate topic modeling in phone conversations.Other inventorsSee patent -
Desired signal spotting in noisy, flawed environments
Issued 10504541
There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the…
There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.
Other inventorsSee patent
Recommendations received
4 people have recommended Sean
Join now to viewMore activity by Sean
-
Yesterday I led a full day wellness workshop at Epic Sales Partners in Irvine and it was a blast! I gave a presentation on how important retraining…
Yesterday I led a full day wellness workshop at Epic Sales Partners in Irvine and it was a blast! I gave a presentation on how important retraining…
Liked by Sean Storlie
-
We've seen a surge in demand for Zelta from companies deploying customer support AI with products like Intercom's Fin, and it's for an interesting…
We've seen a surge in demand for Zelta from companies deploying customer support AI with products like Intercom's Fin, and it's for an interesting…
Liked by Sean Storlie
-
Congratulations to this year's Forensic Interviewer Week award recipients: * Champion for Children - Regina Dismuke, Hero House CAC, GA * Child…
Congratulations to this year's Forensic Interviewer Week award recipients: * Champion for Children - Regina Dismuke, Hero House CAC, GA * Child…
Liked by Sean Storlie
-
🎉 💥 HIRING ALERT!!! 💥 🎉 The Chainguard Enablement team is expanding and we need you! Are you a former Sales Engineer or Customer Success…
🎉 💥 HIRING ALERT!!! 💥 🎉 The Chainguard Enablement team is expanding and we need you! Are you a former Sales Engineer or Customer Success…
Liked by Sean Storlie
-
Cold plunge. So good after a workout. Cuts recovery time in half! Speaking of which, any other goal oriented folks on my feed got a July workout…
Cold plunge. So good after a workout. Cuts recovery time in half! Speaking of which, any other goal oriented folks on my feed got a July workout…
Liked by Sean Storlie
Other similar profiles
-
Josh Weisman
Developmental SaaS Leader
Connect -
Conor McGuinness
Connect -
Gillan Hawkes
Connect -
Ronan Keaveney
Connect -
Daniel Urban
Connect -
Beatrice Casanova
Connect -
Michael Ignaczak
Product Manager at Invoca
Connect -
Victor Borda
Connect -
Collin Middleton
Senior Director of Product Management at Invoca
Connect -
Vivianna Day
Connect
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More