While randomised control trials like A/B tests are the gold standard for causal inference, there are many situations where they’re not appropriate or even possible to run. Geo-experiments (where we apply the treatment to specific geographic regions) can act as a quasi-experimental alternative when conventional A/B tests aren’t feasible. In this presentation we’ll introduce geo-experiments, the common statistical models used to construct synthetic controls for geo-experiments, as well as some of the methods we use at ASOS to accelerate the pace of geo-experiments we run.
Speaker Bio: Conor is a Machine Learning Scientist with a background in statistics working on the marketing science team at ASOS. His work in the marketing science space has involved developing experimentation frameworks to streamline online testing as well as machine learning methods for digital ads optimisation.
RecordedAug 10 202133 mins
Your place is confirmed, we'll send you email reminders
Many firms have a large document corpus made up of both digitized and raw images. Now more than ever, financial institutions are turning towards unstructured data sources to capture additional attributes in order to, ultimately, adjust or confirm their analyses and discover new trends and insights. Many organizations rely on individuals to read sections of these documents or search for relevant materials in an ad hoc manner, with no systematic way of categorizing and understanding the information and trends.
Join us for this Dataiku session on interactive document intelligence, where we will showcase a modular and reusable pipeline to rapidly and automatically digitize documents, extract text, and consolidate data into a unified and searchable database. We will focus on NLP techniques applied to prepare, categorize, and analyze textual data based on themes of interest (in this project: ESG), with additional theme modules available. Lastly, we will demo a purpose-built dashboard to provide business users with a simple and interactive tool to analyze high-level trends and drill down into aggregated insights.
Dr. Robert Coop, General Manager of Machine Learning, phData / Doug Bryan, AI Strategist, Dataiku
HR is an often overlooked but rich source of valuable AI use cases such as writing better job postings, identifying key attributes of successful new hires, and attrition management. There is potential for huge benefits when it comes to AI in HR to support collaborative teams and employee retention in addition to keeping job listings competitive.
Join Dataiku and phData as we walk you through a use case of a human resources team at a major medical device manufacturer that needed a more robust data analytics solution as they looked for ways to accurately predict manager performance. phData built a fully functioning model that delivers measurable business value, complete with visualizations and executive dashboards.
Difficultés d’approvisionnement, rupture de stocks, allongement des délais de livraison, insatisfaction des clients... Plus que jamais, La crise COVID a mis en lumière la nécessité pour les entreprises de superviser et d’optimiser leurs chaînes d’approvisionnement et de de distribution, pour prévenir les perturbations éventuelles et élaborer les plans d’actions opérationnels.
Pour répondre à des enjeux de plus en plus complexes, Eulidia est convaincu que l'intelligence artificielle se positionne comme un moteur essentiel de la transformation de la Supply Chain et comme un levier d’innovation et de compétitivité pour les acteurs du marché qui décident d’investir !
Avec le concours de Dataiku, ce webinar vous éclairera sur les étapes clés de ce programme de modernisation
-Modern AI : Retours d’expérience
-Flexibilité et performance apportée par une plate-forme Analytics telle que Dataiku / Snowflake
-Les clés de la modernisation de la Supply Chain
-Supply Chain Analytics : quels cas d’usages et quels bénéfices ?
Michael Ernest, Director of Solution Architecture at Dataiku
In this demo we'll walk through a DSS project that features a variety of integrations with the AWS platform as well as several key services. The demonstration will highlight key performance benefits built into DSS when operating in the AWS environment, and integrations with AWS services, including Redshift, EMR, and EKS.
Christina Hsiao, Senior Product Marketing Manager @ Dataiku with Guest Asha Dinesh, Market Impact Consultant @ Forrester &
When it comes to building a modern AI platform, organizations shouldn’t spend time, energy and resources cobbling together tools across the AI lifecycle, which ultimately results in losing the larger picture of the full data pipeline (not to mention adds technical debt).
This webinar unpacks the results of The Total Economic Impact™ Of Dataiku study (conducted by Forrester Consulting and commissioned by Dataiku) that quantifies and solidifies some of the benefits that Dataiku customers experience in leveraging one, central platform to systemize the use of data for Everyday AI, including:
- 423% ROI over three years (with a payback period of < 6 months)
- 75% time savings for data engineers and data scientists
- 90% reduction in manual, repeated reporting tasks
Do you want to know what your customers are talking about your airline? What services do they like? And what puts them off? We developed a workflow in Dataiku DSS that uses NLP to determine the sentiment behind the tweets and a webapp that allows the end user to view the results. We will walk you through how we used the tweets, did some text cleaning, built models to classify the sentiment, and if time permits - also web scraping to extract airline online reviews.
Minosh Salam, Director, Business and Strategy @ DataQraft, Umut Şatir Gürbüz, Senior Sales Engineer @ Dataiku
This webinar will go in-depth on the trends that will continue to dominate Enterprise AI, particularly when it comes to organizational changes in businesses. In the second part of the webinar we will have a Dataiku demo which will showcase the capabilities of the platform and its recipes through an advanced analytics use case.
- Minosh Salam, Director, Business and Strategy at DataQraft
- Umut Şatir Gürbüz, Senior Sales Engineer at Dataiku
Please be aware that by registering for this webinar, you agree to have your personal information shared with Dataiku's partner DataQraft. They may contact you with information that could be of interest to you.
Dan Darnell, Head of Product Marketing Dataiku and James Kobielus, Senior Research Director, Data Management
Organizations everywhere are automating the development, deployment, monitoring, and governance of mission-critical machine learning (ML) and other artificial intelligence (AI) applications.
Operational data science is a collaborative process that increasingly goes under the name of MLOps. Organizations are bringing the latest MLOps into their data science workflows to augment the productivity of data engineers, statistical modelers, and other highly skilled personnel. Mature enterprise MLOps processes leverage cloud-native infrastructure to scale the deployment, monitoring, and management of statistical models and code builds into production applications.
Join Dan Darnell from Dataiku and TDWI’s senior research director James Kobielus for this webinar to learn how enterprises can succeed in using mature MLOps practices across their entire data science pipelines to speed deployment of their most sophisticated AI applications.
Key topics that he will discuss include:
- Business opportunities that are driving demand for MLOps
- Key investments in data ingestion, cleansing, preparation, and modeling technologies that are essential for organizations to succeed with MLOps
- Challenges that organizations face when implementing MLOps within their established data science processes
- Principal operational metrics that organizations must monitor and track to ensure the success of their MLOps initiatives while mitigating associated operational, legal, and regulatory risks
Maria Prosviryakova - Senior ML Engineer at Skyscanner
Looking for places to travel next in these uncertain times? Interested in finding great deals in safe destinations? Skyscanner's personalised recommendations can save your precious decision time! In this talk, Maria Prosviryakova, Senior Machine Learning Engineer at Skyscanner, will share the journey from a simple yet impactful collaborative filtering model to deep learning-powered destinations recommendations. Maria will touch upon the architecture of the real-time recommender system that relies on ML pipelines and MLflow and is orchestrated using Apache Airflow. She will also discuss challenges faced on the road to production, and how the personalised recommendations increased Skyscanner's engagement metrics.
Maria Prosviryakova is currently working as a Senior ML Engineer at Skyscanner. Maria holds an MS degree in Statistics and has 7+ years of experience working as a data scientist across different industries and locations: finance in New York, e-commerce in Buenos Aires and the travel industry in Barcelona. She now specialises in recommender systems and ML in production.
Only 27% of data professionals say their organization has formal training and education to help staff understand the roles data, machine learning, and/or AI play within the business, according to a Dataiku AI maturity survey. What’s standing in their way? In this webinar, Conor Jensen, VP of Data Science, Americas at Dataiku will unpack key challenges and trends for staffing the AI enterprise, including this aforementioned lack of formal upskilling programs, difficulty hiring data talent, a lack of specificity around the business’s AI needs, and more.
Timm Grosser, BARC Head of Consulting & Sr Analyst
‚Artificial Intelligence‘ ist bereits ein wesentlicher Bestandteil unseres Lebens und öffnet Pforten für Innovation. Wir sehen erstaunliche Errungenschaften in allen Bereichen des Lebens, nicht nur in Hightech-Branchen wie Weltraumtechnik und Robotik, sondern in allen Bereichen. Zuletzt nutzen wahrscheinlich Sie auch bereits AI in einer App auf dem Smartphone oder als intelligenten Assistent in Form der Alexas, Siris oder Cortanas dieser Welt. AI ist allgegenwärtig und die Durchdringung von AI wird weiter zunehmen. Es ist nicht schwer abzuleiten, dass AI starke Auswirkungen auf Wirtschaft und die Unternehmen mit sich bringt. Sie eröffnet Chancen, bringt aber auch viel Stoff für Diskussion mit sich.
-Doch wo stehen Unternehmen heute überhaupt in der Nutzung von AI?
-Was müssen diese mitbringen, um AI wirklich nutzen zu können?
-Wo liegen die größten Hürden in der Implementierung von AI und was sind Lösungsansätze?
-Wo wird AI heute eingesetzt in Kontext von Data & Analytics?
Diese und weitere Fragen klären wir im Webinar.
Triveni Gandhi, Data Scientist & Paul-Marie Carfantan, AI Governance Manager
Responsible AI is a topic of growing interest for data practitioners for both research and the industry, especially in the context of ML Fairness. While implementing standardized fairness techniques into existing pipelines can be a challenge, Dataiku offers strategic resources for data scientists and analysts to seamlessly incorporate ML Fairness techniques into their workflows.
Join Triveni Gandhi, Senior Industry Data Scientist, and Paul-Marie Carfantan, AI Governance Manager, for this webinar to learn about practical applications of ML Fairness and how they support broader Governance, Responsible AI, and MLOps concepts in the organization.
Want to judge whether your recipe will be a hit? Or in general, what user-generated content is likely to lead to high engagement? This Dataiku Community on-demand talk will walk you through the basics of text pre-processing and using NLP to predict which recipes are likely to be highly rated. By the end of the talk, viewers should be able to take away the reasoning and key steps of the project and apply NLP to their own prediction problems.
This webinar has something for everyone, whether technical or not. On the business side, you’ll get an overview of how to better manage your infrastructure spend while providing the compute your analysts and data scientists need as well as a practical demonstration of how autoscaling your data processing infrastructure provides the horsepower you need without breaking the bank.
On the technical side, if you like Spark for processing big data and Kubernetes for scaling and managing containers but you haven’t run Spark on Kubernetes yet, this is the webinar for you. In this one hour session, you’ll learn:
- Why Kubernetes is a great scheduler for Spark jobs
- How to quickly spin up a managed Kubernetes cluster on AWS and run you first Spark job from your environment
- How Dataiku lets data scientists spin up Kubernetes clusters and run Spark jobs with just a few mouse clicks
Dr Ir Renee Boerefijn -Bunge Loders Croklaan, Carsten Ersch -Friesland Campina, Dan Roozemond -EyeOn, Shaun McGirr -Dataiku
Covid reminded us that the food industry is critical infrastructure. In this webinar we share two stories from practice where digital innovation drives improvements with real-life impact.
For Bunge Loders Croklaan, Covid triggered digital innovation to protect operational continuity. They started an agile approach with EyeOn towards a digital twin with surprisingly immediate commercial benefits: accelerated customer solutions and internal synergy, as well as excitement and fun for the teams with the supporting partners. Bunge do not accept the status quo, but creatively work through and around challenges.
Also within Friesland Campina, the growing focus on the digitalization of R&D processes has fueled innovation around products and processes. Data and analytics democratization are key enablers in this digitalization process but delivering these at scale in a complex organisational setup is often challenging and requires attention at specific times within the digitalization process.
These stories show how platforms of innovation, like Dataiku, help foster and accelerate innovation. These leading companies in the food industry look for improvements every day and digitalization enables them to take exciting steps forward!
- Dr Ir Renee Boerefijn, Director of Innovation @ Bunge Loders Croklaan
- Carsten Ersch, Digital R&D Lead @ Friesland Campina
- Dan Roozemond, Data Science Lead @ EyeOn
- Shaun Mcgirr, AI Evangelist @ Dataiku
Please be aware that by registering for this webinar, you agree to have your personal information shared with Dataiku's partner EyeOn. They may contact you with information that could be of interest to you.
In this talk, Moumita Bhattacharya, Senior Data Scientist at Etsy, will present an overview of recommender systems, including traditional content based and collaborative filtering. She will touch upon some current trends and breakthroughs in this area and provide an overview of how recommendations are developed at Etsy. Specifically, she will discuss Etsy's journey from linear ranking models to a non-linear deep neural network ranking model, the challenges they faced and the lessons they learnt.
Moumita Bhattacharya is a Senior Data Scientist at Etsy, a two-sided marketplace for buyers and sellers. At Etsy, Moumita is the tech lead of a team that develops recommendation systems to show relevant items to Etsy users. Recently, she developed a ranking method to improve conversion rates and gross merchandise sales of the company. As a part of another project, she developed custom objective functions to optimize for metrics beyond relevance and is also incorporating different contexts in recommendations. Moumita has a PhD in Computer Science with a focus on Machine Learning and its applications in disease prediction and patient risk stratification.
Dataiku is the world’s leading platform for Everyday AI, systemizing the use of data for exceptional business results. Organizations that use Dataiku elevate their people (whether technical and working in code or on the business side and low- or no-code) to extraordinary, arming them with the ability to make better day-to-day decisions with data.
More than 450 companies worldwide use Dataiku to systemize their use of data and AI, driving diverse use cases from fraud detection to customer churn prevention, predictive maintenance to supply chain optimization, and everything in between.