StampedeCon AI Summit

October 17, 2017 - St. Louis, MO


Explore the applications of artificial intelligence for your organization. The world of AI is here, will you be a part of it?


The Growth of AI

The applications of artificial intelligence in the creation of new products and optimizing business operations are growing and boundless. Advanced machine learning techniques, underpinned by the fundamentals of data science, are bringing predictive models to new levels of accuracy and helping drive new products, capabilities, and discoveries.


What do we KNOW?

You have been collecting and reporting on your data, looking backwards in time. Develop predictive models to find patterns and increase your understanding of the factors that drive your business.


How do we LEARN more?

Advanced machine learning capabilities, such as Deep Learning, are advancing our ability to train predictive models. True learning comes as we act on predictive models and learn what data we could add to models to improve their accuracy.

How do we PREDICT?

Predictive analytics allows us to learn from past business data to predict future outcomes and opportunities. Iteratively refine your models based on actual outcomes and new data. Model, prescribe, act, measure, repeat.

Join the Inaugural AI Summit

Hear from expert speakers and network with other regional data scientists and machine learning practitioners at the inaugural StampedeCon AI Summit on October 17, 2017 in St. Louis, MO


Premier Sponsors

Community Sponsors


These sessions are subject to change.
More sessions are to be added.
Speaker information will be added soon.

Foundations of Modeling and Machine Learning
This presentation will cover all aspects of modeling, from preparing data, training and evaluating the results. There will be descriptions of the mainline ML methods including, neural nets, SVM,. boosting, bagging, trees, forests, and deep learning. common problems of overfitting and dimensionality will be covered with discussion of modeling best practices. Other topics will include field standardization, encoding categorical variables, feature creation and selection. It will be a soup-to-nuts overview of all the necessary procedures for building state-of-the art predictive models.
Predicting Outcomes when your Outcomes are Graphs
In many modern applications data are collected in unusual form. Connectome or brain imaging data are graphs. Wearable devices measuring activity are functions over time. In many cases these objects are collected for each individual or transaction leaving the statistician with the challenge of analyzing populations of data not in classical numeric and categorical formats in big spreadsheets.

In this talk I introduce object oriented data analysis with an application we recently developed for regression analysis. This talk will be aimed at the general data scientist and emphasis on the concepts and not mathematical detail.

Intelligent Customer Engagement for the Digital Marketplace Using Machine Learning
As products continue to become service-oriented, customer engagement becomes increasingly critical for obtaining long-term customer loyalty. Digital marketplaces are increasingly struggling to maintain customized customer engagement as their businesses scale. This presentation will walk through the how customer-engagement relates to the three-legged stool:

  • increase revenue
  • increase efficiency
  • increase customer experience

It will discuss tools and techniques used in an applied setting to facilitate engagement through automated analysis and intervention. In particular, it will focus upon using machine learning to figure out:

  • customer profiles and segments
  • customer workload patterns
  • consumer lifecycles

Finally this talk will discuss how businesses can leverage these types of models through taking intelligent actions on their ditial platforms to help solve problems such as:

  • preventing customer churn
  • product cross-sale recommendations
  • workload prediction
  • preventing abuse and malware
Novel semi-supervised probabilistic ML approach to SNP Variant Calling
This talk aims to dive into technical details in machine learning model development, implementation and values it bring to Monsanto breeding pipeline. We genotype over 100 million seeds a year in order to save field resources and product development cycle time. Automation and high throughput production from the lab becomes key to R&D success. In house predictive model development incorporated random forest ensemble based approach with additional features derived from gaussian mixture model. The results show over 95% accuracy with less than 1% false positives/negatives. Model is highly generalizable with over 10 million data points being trained and tested on. The model also offers probabilistic approach to present genotypes in a more meaningful way and help enhanced downstream genomics analyses. The talk targets audience who are in breeding, genetics, molecular biology, and data scientists who are interested in practical applications.
Getting Started with Keras and TensorFlow using Python
This technical session provides a hands-on introduction to TensorFlow using Keras in the Python programming language.  TensorFlow is Google’s scalable, distributed, GPU-powered compute graph engine that machine learning practitioners used for deep learning.  Keras provides a Python-based API that makes it easy to create well known types of neural networks in TensorFlow.  Deep learning is a group of exciting new technologies for neural networks. Through a combination of advanced training techniques and neural network architectural components, it is now possible to train neural networks of much greater complexity. Deep learning allows a model to learn hierarchies of information in a way that is similar to the function of the human brain.

This presentation will begin by showing how to use TensorFlow with Python 3 on commodity GPU/CPU hardware.  The presentation also provides a brief overview of running TensorFlow from Amazon AWS.  Neural networks will be demonstrated for the classic data science problems of classification and regression.  Additionally, we will discuss how neural networks can make predictions on common data sets and how to interpret those results.  While neural networks can adequately perform classic data science tasks, they truly shine in the areas of image recognition and time series processing.

This presentation will also introduce convolution neural networks for computer vision, which allows computers to recognize images.  The most state-of- the-art deep learning algorithms are capable of identifying multiple objects within a single image.  Some algorithms automatically generate a descriptive caption for an image.

The session will also include long short term memory (LSTM) for time series, which is a very broad machine learning discipline that deals with data where events occur over time.  One of the most common areas of time series prediction is financial analysis and prediction over time.  However, any series of events can be modeled as time series.  Other applications of LSTM include natural language processing (NLP) and speech recognition.  This presentation will cover three examples of TensorFlow: regular classification, computer vision and time series.

Location: Eric P Newman Education Center, Washington University Medical School

320 S Euclid
St. Louis, MO 63110


Metro Parking Garage
This is EPNEC’s primary parking garage.
Located at the corner of Taylor and Children’s Place Avenues.
Daily Rate is $15 – Accepts Cash and Credit Cards
Click Here for Printable Map and Directions

EPNEC is an IACC-certified conference center on the campus of Washington University Medical Center in St. Louis, Missouri

Eric P. Newman Education Center

Eric P. Newman Education Center
PARK in Metro Parking Garage at 4560 Children’s Place, St. Louis, MO 63110


Note: Tickets are non-refundable.

Subscribe to our mailing list

* indicates required
Participate in StampedeCon