Building Machine Learning Algorithms That We Can Trust

How to Explain any machine learning model in minutes — with confidence and trust? Here's How:

“To be or not to be” became the mantra of thought and self-reflection in the philosophical arena when Hamlet uttered these words in Shakespeare’s famous tragic play. In today’s business world, driven by decisions made by artificial intelligence, that mantra has changed into “to trust, or not to trust”.

With recent AI debacles making news, the question of lack of transparency and increasing biases in AI models have come to light. With recent examples where the AI system stated that the highly polluted air was safe to breathe whereas, in reality, it was highly dangerous or the instance when the AI system stated that a certain patient didn’t have cancer when in fact the patient did have cancer and died or the instance when the AI system identified a certain transaction as fraud whereas it was a completely legitimate transaction creating unnecessary trouble for the customer, there is clearly something wrong.

These debacles are increasing every day with the wide use of AI and are caused by, none other than, our blinded trust into these AI systems, but now it’s time to take action!

The current business landscape is still very skeptical when it comes to implementing and trusting these AI systems. Many companies have initiated the process, but have yet to realize the value. This is mainly due to the understanding gap between data science teams and business stakeholders.

We talked to many business stakeholders over the past few months, that are on the receiving ends of these predictions, and found the inability of the data scientist to explain the why and how behind AI systems predictions to be the biggest factor of mistrust and skepticism towards the data science initiative.

People in the data science teams are highly technical with a knack for complexity to signal the extent of their skillset. However, business stakeholders are the complete opposite: they don’t care about the technology used, but how the results generated by the model tie-up with their business goals and KPIs.

This is impossible to achieve unless the data scientist can answer these essential questions:

1. Why should I trust the results generated by the model?

2. What was the rationale used by the model to generate the results?

3. What are the upside and the downside of using the model in production?

4. Do the results align with the business logic or not?

Only after answering these questions, the data scientist can bring recommendations to the business user, and expect to make some progress.

To solve this, the data scientist has two choices:

1. Explain the black-box models by building an interpretable model on top of it. This is the logic behind LIME & SHAP. SHAP is more widely used since it guarantees a fair distribution of contribution for each of the variables and has a wide array of graphs. Sadly, this approach requires a lot of iterations, lacks interactivity and is not scalable especially when you’re dealing with sensitive datasets and decisions. More than that, the visualizations are not appealing and interactive. Their static nature creates an even further divide between the data scientist and the business stakeholder. The absence of dynamic and interactive graphs makes it extremely difficult to generate value from SHAP or LIME, thus a better way to use these techniques is required.

2. Use interpretable models: instead of using black-box models such as deep neural networks, a data scientist can try to optimize simpler models like logistic regression or decision trees to make predictions. There will be a trade-off in accuracy and interpretability, but the data scientist will need to decide what is important to generate value and will need to focus on the marginal benefits between the two models. If the marginal increase between accuracies is not significant, it’s more ideal to implement simpler models and tie the predictions directly with business KPIs. Sadly, with the increasing complexity in the data, we’re collecting today, simpler models do not perform well.

So the question arises:

Is there a better way of building trust in our machine learning models?

Yes, there is! At mltrons, our vision is to increase the adoption of AI and accelerate towards achieving singularity. To make that happen, we embark on the mission to help data scientists build AI algorithms that are understandable, explainable and unbiased.

This will ensure that everyone affected by AI will be able to understand why decisions were made and ensure the AI results were unbiased, accurate and free of any logical inconsistencies.

To fulfill our mission, we’re creating a plug-n-play explainable AI system for data scientists that will specialize in understanding, explaining, visualizing and validating the why and the how behind machine learning predictions — in a fully immersive and interactive manner.

The system will aim to help the data scientist and business stakeholders build trust in the AI system and make fully informed decisions.

Figure 1.1(Disclaimer: The Author is the CEO/Co-Founder @ mltrons)

What differentiates mltrons xAI engine from alternatives currently in the market is our system’s ability to function across multiple datasets and custom-built models.

Instead of making scientists switch to a new stand-alone system, we aim to implement our system within the current workflow of data scientists.

This means that data scientists can now bring in their Jupiter notebooks, data sources — Amazon, MySQL, HDFS and custom-built models using XGBoost, CatBoost, PyTorch, TensorFlow, SageMaker to the mltrons engine — mltrons engine will take in their input and will work as an added layer to provide explainability on how these algorithms work, think and output results.

The data scientist will be able to then explain the results in simple business-friendly language, ideally understood by anyone, through our interactive visualizations, reports, and shareable dashboards.

To supercharge our mission, we’re offering our system for free to the first hundred subscribers who will sign-up using the form below. We will be launching this in another month and will keep improving it by working together with our community. So if you believe in increasing AI adoption and building more trust in machine learning algorithms, click on the link: SIGN-UP FOR EARLY ACCESS.

If you have any questions about the technology, please don’t hesitate to reach out to us at [email protected] or visit this website to learn more.

(Disclaimer: The Author is the CEO/Co-Founder @ mltrons)