Get Your
Return on AI
With Dataiku

Dataiku is the leading platform for Everyday AI, driving results by enabling data experts and domain experts to build data — from advanced analytics to Generative AI — into their daily operations.

Get Your
Return on AI
With Dataiku

Dataiku is the leading platform for Everyday AI, driving results by enabling data experts and domain experts to build data — from advanced analytics to Generative AI — into their daily operations.

Logo
Logo
Logo
Logo
Logo
Logo
Logo
Logo

5 Steps to Unlocking ROAI

1

Real-Life ROAI Stories

More than 600 customers get measurable ROAI using Dataiku for diverse use cases.

30x FASTER

The FP&A team at Standard Chartered Bank uses Dataiku to make their analysts 30x more productive.

60%-70% TIME SAVED

Heraeus uses Generative AI to support its lead identification and qualification process, ultimately saving time and increasing sales conversions.

11%-36% CHEAPER

Vestas uses Dataiku to reduce express shipment costs for its wind turbine parts by 11%-36%.

10x MORE MODELS

MandM Direct uses Dataiku to operationalize 10x more models versus a code-only approach.

$18 MILLION SAVED

SLB uses Dataiku to notify talent managers about at-risk populations, saving $18,000,000+ by maintaining high-value employees.

20x FASTER

U.S. Venture uses Dataiku to analyze new markets 20x faster.

10% LESS WASTE

Detailresult uses Dataiku to fully automate the production of daily predictions for over 100 food retail stores, reducing waste by 10%.

-50% DOWNTIME

Oshkosh Corporation uses Dataiku to achieve a 50% reduction in downtime and support costs over the life of its vehicles.

7.5x FASTER

Bankers’ Bank uses Dataiku to report on cross sell effectiveness 7.5x faster.

100s OF DATA SOURCES

Moderna uses Dataiku to generate targeted and actionable medical insights around combating infectious diseases from hundreds of structured and unstructured data sources monthly.

-50% TIME SPENT

Aviva’s internal audit division uses Dataiku to cut the time spent per audit by 50% — while increasing quality.

MORE TRUST

Cox Automotive uses Dataiku to power the Kelley Blue Book (KBB) Fair Repair Range, automating the process of updating the models and monitoring the results in a unified ecosystem to ensure consumers can always make a trusted and informed decision.

9x FASTER

Action uses Dataiku to deploy sales forecasting models 9x faster.

IMPROVED SAFETY

Roche uses Dataiku to improve patient safety by predicting data monitoring needs in clinical studies.

1/

1

Real-Life ROAI
Stories

More than 600 customers get measurable ROAI using Dataiku for diverse use cases, from predictive maintenance and supply chain optimization to quality control in precision engineering, marketing optimization, Generative AI use cases, and everything in between.

30x FASTER

The FP&A team at Standard Chartered Bank uses Dataiku to make their analysts 30x more productive.

60%-70% TIME SAVED

Heraeus uses Generative AI to support its lead identification and qualification process, ultimately saving time and increasing sales conversions.

11%-36% CHEAPER

Vestas uses Dataiku to reduce express shipment costs for its wind turbine parts by 11%-36%.

10x MORE MODELS

MandM Direct uses Dataiku to operationalize 10x more models versus a code-only approach.

$18 MILLION SAVED

SLB uses Dataiku to notify talent managers about at-risk populations, saving $18,000,000+ by maintaining high-value employees.

20x FASTER

U.S. Venture uses Dataiku to analyze new markets 20x faster.

10% LESS WASTE

Detailresult uses Dataiku to fully automate the production of daily predictions for over 100 food retail stores, reducing waste by 10%.

-50% DOWNTIME

Oshkosh Corporation uses Dataiku to achieve a 50% reduction in downtime and support costs over the life of its vehicles.

7.5x FASTER

Bankers’ Bank uses Dataiku to report on cross sell effectiveness 7.5x faster.

100s OF DATA SOURCES

Moderna uses Dataiku to generate targeted and actionable medical insights around combating infectious diseases from hundreds of structured and unstructured data sources monthly.

-50% TIME SPENT

Aviva’s internal audit division uses Dataiku to cut the time spent per audit by 50% — while increasing quality.

MORE TRUST

Cox Automotive uses Dataiku to power the Kelley Blue Book (KBB) Fair Repair Range, automating the process of updating the models and monitoring the results in a unified ecosystem to ensure consumers can always make a trusted and informed decision.

9x FASTER

Action uses Dataiku to deploy sales forecasting models 9x faster.

IMPROVED SAFETY

Roche uses Dataiku to improve patient safety by predicting data monitoring needs in clinical studies.

2

See How You Stack Up on ROAI

We, along with our partner Databricks, surveyed 400 senior data and AI professionals in 2023 on the hottest topics in the industry. Answer five short questions to see the results and how you compare when it comes to spending on data and AI efforts plus ROAI from those initiatives.

We surveyed 400 senior data professionals on their ROAI — answer five short questions to see how you compare.

3

Forrester:
Dataiku Drives 413% ROI
on Data & AI Projects

Forrester: Dataiku Drives 413% ROI

The Total Economic Impact™ Of Dataiku (conducted by Forrester Consulting and commissioned by Dataiku) quantifies and solidifies some of the benefits that Dataiku customers experience:

  • 70% time reduction on data analysis, extraction, and preparation.
  • 42% time reduction for model lifecycle activities (training, deployment, and monitoring).
  • Reduced cost for supplementary analytics tools and consultants.
  • Improved decision making due to democratization of data usage and access.
  • $23,500,000 net present value over three years.

4

GET YOUR ROAI WITH DATAIKU

Dataiku is the only platform on the market that unifies all your data work, from analytics to Generative AI, for maximum ROAI.

Use & Fully Leverage Your Existing Architecture/Ecosystem

Fully Leverage Your Existing Architecture

Dataiku enhances — not replaces — your existing architecture and ecosystem, acting as the central orchestration layer to deliver results with AI at scale. Plus, if you’re looking to modernize your data stack and consolidate disparate tools being used for each point in the data-to-insights process, Dataiku has you covered. Bottom line? Lower cost of ownership for more ROAI.

Dataiku enhances — not replaces — your existing architecture and ecosystem, acting as the central orchestration layer to deliver results with AI at scale.

Accelerate the Pace of AI

Customers routinely cite a 60%-80% reduction in time spent to go from data and AI project ideation to production. At the individual level, common steps go more quickly thanks to Dataiku’s highly intuitive and visual interface.

At the organizational level, Dataiku accelerates progress towards Everyday AI by building a persistent culture of AI development, deployment, management, and reuse. For specific use cases, plug-and-play Dataiku Solutions allow teams to deploy full-fledged AI solutions in days and weeks, not months or years.

Customers routinely cite a 60-80% reduction in time spent to go from data and AI project ideation to production.

 

Bring Generative AI to Life

Dataiku brings enterprise-grade development tools, pre-built use cases, and AI-powered assistants to help everyone do more with Generative AI. The LLM Mesh provides the components in Dataiku that empower IT to take control and help teams build safe, secure, enterprise-ready GenAI applications.

Dataiku brings enterprise-grade development tools, pre-built use cases, and AI-powered assistants via the LLM Mesh to help everyone do more with Generative AI.

5

Accelerate Your Journey
With an ROAI Consultation

Book Your ROAI Consultation

30x FASTER

FP&A at Standard Chartered Bank

On average, two people armed with Dataiku are doing the work of about 70 people limited to spreadsheets. Here’s how they got there.

The Challenge: From 10 to 400 Million Rows
of Data

FP&A at Standard Chartered Bank has had the systems in place to do balance sheet analytics, costs analyses, etc., for many years, but analysis was limited to 10 million rows of data. In addition to finding a solution that leveraged their existing infrastructure investments, the team didn’t want to have to go looking for another tool again in a few years when his team became mature enough to start doing machine learning on their data.

“We got our hands on Dataiku and we said — what can this thing do? Within three to four weeks we managed to turnover a 4.5 billion row table in a single operation. So within a very short period of time we basically achieved our original goal, which was processing data better. But Dataiku made us realize we could do so much more than that. We’ve got an army of people copy and pasting data, and this thing can load up very big stuff. Dataiku allowed us to have different conversations about data.”

Craig Turrell,

Head of P2P Data Strategy & Delivery

Standard Chartered Bank

The Solution: Collective Intelligence
with Dataiku

By 2021, one year into their Dataiku journey, the team was using Dataiku to run three major systems at the bank and to refresh daily Tableau dashboards for all the bank’s finances, a laborious task previously done in spreadsheets. The goal in the coming years will be to continue to upskill people with Dataiku to increase efficiency across more areas of Standard Chartered Bank.

“My goal is to change the way the bank reports. We’ve taken very good accountants, given them Dataiku, and they’re producing brilliant stuff.”

Craig Turrell,

Head of P2P Data Strategy & Delivery

Standard Chartered Bank

60%-70% TIME SAVED

Heraeus: Improving the Lead Pipeline With Generative AI

Heraeus is using the momentum from its Generative AI-driven lead list tool to experiment with the new technology in a governed environment and develop more use cases within the company.

The Challenge: Informal, Manual Processes

Before Dataiku, the process at Heraeus for identifying sales leads was very informal and manual (i.e., searching on Google, brainstorming, etc., which took a lot of time), so the goal was to automate this process via large language models (LLMs) using specific selection criteria. The team asked themselves, “Can we use Generative AI’s creativity to generate new sales leads?” The answer turned out to be yes.

The Solution: An (Effective) GenAI Use Case in Just 5 Weeks With Dataiku

Heraeus partnered with Dataiku to develop a prototype use case which identifies sales leads and fact-checks them thanks to external knowledge. Given that the former sales lead identification process was immensely manual and time-consuming, the estimated time saved with the new process leveraging LLMs in Dataiku is 60%-70%. Heraeus has been able to identify targets that they would not have been able to without the tool, demonstrating the efficiency of the use case and quality of the results.

Dataiku features like automation and the possibility to quickly deploy interfaces for end users with Dataiku applications and web apps enabled Heraeus to get this use case up and running very quickly — from initial discussion to implementation in five weeks — in order to focus on the use case and LLM without having to worry about the automation. The team was also very focused on Responsible AI, mitigating the risk of erroneous or obsolete information and always keeping a human in the loop for validation.

“Timing was fast and pivotal here. Dataiku made it possible in such a short timeframe and, from a technology capability point of view, we would not have been able to do it without them.”

Jannik Beers,

Commercial Excellence Manager

Heraeus

11%-36% CHEAPER

Vestas: Propelling Sustainable Energy Solutions

With 160 GW of wind turbines to keep in good condition around the globe, Vestas needs to ensure that it can ship the right parts to the right sites within the right window of time — all without incurring unnecessary costs.

The Challenge: To Express Ship, or Not to
Express Ship?

Vestas offers both regular and express shipping to its customers — but what happens when the company uses express shipping to service repairs that are not, ultimately, time-sensitive? The Service Analytics found that 52% of express-shipped materials were not being put to use for at least four months, meaning the cost of express shipping (which often involves transporting parts by air) is wasted.

The Solution: Changing Shipment Patterns Across the Company With Dataiku

Within just about one month, the Service Analytics team was able to leverage Dataiku to build and deliver a recommendation tool that would help dispatchers and planners know whether, for a given request, they should use express shipping. The solution includes a deployed machine learning model, APIs, and a stand-alone application for end-users.

Though the savings generated by the express shipping recommendation model will only fully materialize over time, when globally implemented, the solution is estimated to reduce express shipment costs by 11%-36%.

“The Dataiku team’s systematic approach towards converting business asks to requirements, assessing feasibility, identifying alternate approaches, and building a machine learning solution and deployment along with documentation helped us learn how to take a structured approach towards designing and building machine learning solutions. This will help our team further along our journey towards building more ML-based solutions.”

Mohamed Musthafa Shahul Mohamed,

Data Science Lead

Vestas

10x MORE MODELS

MandM Direct: Managing Models at Scale

MandM Direct uses Dataiku and Google Cloud Platform (GCP) to build and maintain a data science practice that operationalizes 10x more models versus a code-only approach, supporting a wide range of use cases.

The Challenge: Scaling Out AI Deployment

MandM Direct is one of the largest online retailers in the United Kingdom, delivering more than 300 brands annually to 25+ countries worldwide. Their accelerated growth meant more customers and, therefore, more data, which magnified some of their challenges and pushed them to find more scalable solutions.

For example, MandM’s first machine learning models were written in Python (.py files) and run on the data scientist’s local machine, and they needed a way to prevent interruptions or failure of the machine learning deployments.

The Solution: Breaking Data Silos & Democratizing AI
With Dataiku

The data team at MandM Direct is now able to deliver a variety of solutions to business problems, from adtech to customer lifetime value, whether that’s a dashboard, a more detailed piece of analysis, or a machine learning project deployed in production.

MandM now has hundreds of live models, all with visibility into model performance metrics, clear separation of design and production environments, and many more MLOps capabilities built into the platform.

“Having a platform like Dataiku allows our data scientists to focus on building cool things, not spending hours and hours on maintenance and making sure things are running. With workflows deployed in Dataiku, we save literally days of work every month.”

Ben Powis,

Head of Data Science

MandM Direct

$18 MILLION SAVED

SLB: Optimizing the End-to-End Talent Lifecycle

SLB's People Analytics team uses Dataiku to better equip its talent management teams globally (reducing the time invested in training by months and years) and improve talent retention (saving millions of dollars annually).

The Challenge: Bringing ML to HR

Every year, more than 500,000 people apply to work at SLB and, of those, only 2%-3% of them are selected into their talent pool. With superior talent and a vast data warehouse available to SLB’s talent management teams across the globe, the team wanted to use machine learning to solve some of their most pressing HR challenges.

The Solution: Enhancing Talent Retention

Just like any modern company, SLB is focused on improving employee retention. Using Dataiku, they have built data pipelines from troves of data (i.e., across salary information, vacation data, performance and career stagnation information) to notify talent managers across the company about at-risk populations so they can effectively take actions as early as possible. They also provide the talent managers with insights on how they can improve the environment for their employees, such as salary, skill, or schedule changes.

Each year, the cost of unplanned employee attrition costs SLB $80-$200 million but, with the predictive model in Dataiku, the company has been able to retain between $18-45 million of that total thanks to the work the People Analytics team has done to identify and maintain high-value employees.

“Dataiku is a true partner. It’s a great product that makes sense for our team — it’s not static, it has a great product vision and roadmap, and the best part is how willing the Dataiku team is to help us.”

Modhar Khan,

Head of People Analytics

SLB

20x FASTER

U.S. Venture: Upskilling Analysts

U.S. Venture uses Dataiku to streamline their data efforts, implement a culture of reuse, and — for their warehouse optimization solution — achieve a 95-97% time savings.

The Challenge: Data-Driven Geographic
Expansion Decisions

U.S. Venture is regularly expanding to new markets, and part of that process involves creating an optimal logistics network, identifying potential customers, and pinpointing market risks and opportunities.

Before Dataiku, this modeling would take 60-100 hours per market. Because the process was so labor intensive, it was difficult to keep pace with the business, providing leaders with recommendations from machine learning models to guide complex decisions being made related to how to enter a new market.

The Solution: Maximizing Productivity With Reusable Processes

U.S. Venture used Dataiku to create end-to-end, repeatable flows, reducing the effort and increasing the collaboration and accuracy for this use case. Now, using Dataiku, the team is able to analyze a new market in just three hours.

Having Dataiku enables the team to source, cleanse, model, and share repeatable data science solutions without needing to look to a third party for a software solution for each use case. It also opens up the opportunity for the entire team to do data science work and not just formally trained data scientists.

“Now, Dataiku is a standard way of working at U.S. Venture. Our team is excited about what they can accomplish in Dataiku.”

Brian Taylor,

Data and Analytics Team Manager

U.S. Venture

10% LESS WASTE

Detailresult: Automating Food Store Predictions

Detailresult used Dataiku to train and maintain demand prediction models across hundreds of stores, resulting in an almost 30% reduction in out of stock hours, a 10% reduction in waste, and an average of 10-15 minutes of time saved each day in over 100 stores.

The Challenge: More Models, More Problems

The data team at Detailresult found that a SARIMAX model gave them the best predictions for customer demand for fresh bread in their stores. The problem was that the best predictions were the results of a model trained for a specific store and bread type combination.

Having more than 100 stores and several different bread types meant they would need to have hundreds of models in production to produce daily predictions for each store and bread type combination.

The Solution: The Solution: MLOps & Automation With Dataiku

Dataiku allowed the team at Detailresult to fully automate data pipelines and model flows plus save time on model monitoring. If a new store is opened, it is automatically detected, and a new model is specifically trained for it. New sales data is automatically loaded and used for predictions for the following day.

Stores now receive daily predictions for demand for fresh bread, which they can alter if they expect something else based on their personal experiences or other factors not used in the models. In addition to reducing waste and reducing out of stock hours, stores now spend less time ordering bread and more time focusing on products that require more attention and expertise to predict correctly.

-50% DOWNTIME

Oshkosh: Real-Time Predictive Maintenance

Actionable insights produced through analytics projects in Dataiku translate to more than a 50% reduction in downtime and support costs over the life of a vehicle.

The Challenge: Calendar-Based Oil
Change Intervals

Most heavy-duty vehicles typically use calendar-based scheduled intervals (e.g., every six months), without considering the historical operations and current oil quality. However, by triggering an oil change only when needed, customers avoid unnecessary maintenance actions that result in inflated materials costs and reduced vehicle availability.

The Solution: Disrupting the Maintenance Paradigm With Dataiku

Today, engineering teams at Oshkosh Corporation use Dataiku combined with vehicle telematics data and condition-based maintenance (CBM) methods to monitor and model oil degradation, predicting a remaining useful life and prescribing appropriate actions.

Early pilot program results show a potential 2-3x improvement in required maintenance intervals. If extrapolated over the fleets of similar Oshkosh vehicles in operation around the world, this could result in thousands of labor hours and millions of dollars saved for their customers.

“You need collaboration to do data science effectively in the first place. Dataiku facilitates and enables collaboration much better than anything else I’ve seen. It used to just be technical experts and data scientists, but now analysts and management can be involved side-by-side in the process.”

Dr. Michael Schuh,

Chief Data Scientist

Oshkosh Engineering

7.5x FASTER

Bankers’ Bank: Goodbye, Data Silos

Bankers’ Bank leverages Dataiku to increase efficiency and ensure data quality across an array of financial analytics, ultimately reducing the time to prepare analyses and deploy insights by 87%.

The Challenge: Siloed Datasets

As a result of their business model, Bankers’ Bank manages massive amounts of disparate data from various sources (structured and unstructured).

With their previous, spreadsheet-based process, an analysis that tracks how effective each cross-sell was took 16 hours every quarter to prepare, for an annual total of 64 hours spent.

The Solution: Insights in Minutes (Not Days)
With Dataiku

Today, Bankers’ Bank uses Dataiku for reporting and dashboards that had previously been compiled in Excel. With Dataiku, the time spent on validation went down significantly and the report is delivered in a predictable, consistent, and accurate manner and will soon be delivered on a monthly cadence — something that could not have been imagined given the previous work effort.

The savings translates to an actual time reduction of 87% (it now only takes 30 minutes to prepare!). Analysts can now use that extra time to work on other, more high-value projects.

100s OF DATA SOURCES

Moderna: Targeted, Actionable Medical Insights

Moderna's on-demand AI model designed with Dataiku revolutionized the company’s day-to-day operations by surfacing insights in days while also saving analysts 40+ hours per month.

The Challenge: Optimizing the Generative Medical Insight Analysis Process

For Moderna, the pursuit of medical insights is a crucial aspect of their mission to combat infectious diseases. Timely and targeted insights are essential, driving interventions and educational initiatives. However, the traditional approach of manual data collection, involving 200 to 300 monthly entries in free text, presented challenges of inefficiency, time consumption, and difficulty in scaling.

The Solution: Long-Term Value With Nitro

Nitro is Moderna's on-demand AI model designed to analyze medical insights and sentiments from hundreds of diverse data sources. Built to align with Moderna’s medical affairs strategy, Nitro leverages Dataiku’s natural language processing (NLP) capabilities to up the ante. The process involves a seamless integration of recipes, plugins, and Python code to generate insights, which are then visualized using Tableau.

Nitro's capabilities have revolutionized Moderna's day-to-day operations. Rapid response to shifting sentiments from healthcare providers (HCPs) is now possible, reducing the analysis time frame from months to mere days.

“Dataiku's platform plays a crucial role in optimizing the analysis process, ensuring that the insights generated are aligned with Moderna's goals and reflect the sentiments expressed by healthcare providers. This alignment ensures that Moderna can make informed decisions and develop strategies that effectively address the needs and concerns of HCPs, ultimately driving the success of their medical initiatives.”

-50% TIME SPENT

Aviva: Uniting Data Analysts & Auditors

Aviva’s internal audit division uses Dataiku to cut the time spent per audit by 50% — while increasing quality.

The Challenge: Finding the Balance

The 100-employee-strong Aviva audit team seeks to provide a smooth and efficient customer experience without sacrificing the accuracy of the audit process.

Prior to working with Dataiku, the team might work on an analysis for two months before delivering results. While there are advantages to this sort of timeline (most importantly, the time to give attention to detail and consider all possible points of failure), the team was not satisfied with the pace at which it was able to intervene and help out in audit decisions.

The Solution: Finding Gold With Process Mining

With the help of Dataiku’s plug-and-play process mining solution, auditors are now able to make better, more insight-driven decisions.

The value added by process mining has been significant for both analysts and auditors. On the analyst side the greatest benefit has been in terms of time saved — cutting their time spent by about 50%; whereas for the auditors it has been in terms of the quality of the output, allowing them to quickly focus on what matters.

“Process mining allowed us, on the analytical side, to increase efficiencies and deliver the work in half the time and, on the audit side, to increase the quality of the output, because they are able to zoom in on the potential discrepancies or deficiencies in the customer journey.”

Francisco Pavao Martins,

Senior Manager of Data Analytics

Aviva

MORE TRUST

Cox Automotive: Providing Transparent & Reliable Estimates

Dataiku has improved the transparency of the model and input data powering the Kelley Blue Book (KBB) Fair Repair Range (FRR), so suspect data points or model estimates can easily be identified and investigated.

The Challenge: From Manual and Time Consuming

The KBB FRR is designed to provide consumers with a transparent and reliable estimate of the cost of automotive repairs. The FRR is based on data from actual transactions, and it excludes data from warranted repairs, making it a reliable estimate of the cost of repairs.

Before moving to Dataiku, the process of refreshing FRR was manual and time-consuming.

The Solution: … to Unified & Automated
With Dataiku

Dataiku allows Cox Automotive to easily automate the process of refreshing FRR and monitor the results in a unified ecosystem. Plus, with Dataiku’s modular flow environment, the team can add new service and repair categories with ease.

By automatically refreshing the model and saving time each month with Dataiku, data scientists now devote more resources to improving the FRR models for end customers.

“Using scenarios, we were able to automate the entire machine-learning lifecycle and refresh the model monthly. Dataiku also provided many useful tools for monitoring and fine-tuning these models. Using dashboards, we could identify and remove suspect data from the source data. We also monitor the changes in predicted prices month-over-month and investigate any large price swings to identify any potential issues with our estimates. Finally, we were able to share high-level insights with stakeholders.”

9x FASTER

Action: Powering Data-Driven Decisions

Dataiku scientists at Action worked with Capgemini and Dataiku to develop more accurate and transparent forecasting models, faster, ultimately achieving a 900% improvement on forecast runtime.

The Challenge: Manual, Excel-Based Processes

Prior to working with Dataiku, Action was relying on Excel-built algorithms for their forecasting models. The process of deploying the sales forecasting model, which is run every week and realigned once a quarter, was over-complicated as a result.

The process was also, by consequence, relatively slow. It took data experts several days to run the forecast each time, and hours more to realign it several times a year.

The Solution: Sales Forecasting With Dataiku

With Dataiku, which allows the team to test, modify, and redeploy their models routinely and with precision, they brought the runtime of each forecast down to between nine and 14 hours, and then further improved this to between six and nine hours — a time savings of almost 900%.

It’s no small thing for your business team to have a reliable sales forecast. As Dawid Kirsten, BI Consultant for Insights and Analytics at Action, stressed, these are not easy to generate without the right tools. “We have gone from an Excel-based guesstimate of what the forecast should be to 88% accuracy on a 52-week forecast [with Dataiku],” he said.

“If you use a visual recipe, it’s much easier to explain to the business side what’s happening to the data. ‘This is what’s being filtered. This is how it looks.’ You can take them through every step of the path, giving them confidence in the results.”

Dawid Kristen,

BI Consultant for

Insights & Analytics Action

IMPROVED SAFETY

Roche: Predicting Data Monitoring Needs

Roche used Dataiku to create a predictive model based on a set of study criteria that can determine the need for an Independent Data Monitoring Committee (IDMC).

The Challenge: Predicting the Need for IDMCs

Entrusted with monitoring potential risks to patient safety in Roche's clinical study protocols, the IDMC team faced the challenge of foreseeing when an IDMC request would occur. Despite experience and guidelines, predicting this need proved elusive.

The Solution: Empowering the Business & Beyond

Dataiku enabled the consolidation of disparate information, weaving together master data management, clinical trial management, R&D planning, and operational reporting into a coherent data flow. This not only centralized information but also laid the foundation for feature engineering and model training.

As of now, the model resides in hyper-care mode, hurtling towards the Minimal Viable Product (MVP) stage. Though not fully automated and in production, the IDMC team is already reaping the benefits.

Real-time predictions flow into a Tableau dashboard, acting as a radar to narrow down potential IDMCs and optimize workload. The model's success has attracted attention, showcasing the power of data science tools to non-technical users and instilling a sense of data citizenship within the organization.