Timings


Sessions


09:15 AM - 10:00 AM IST

09:15 AM - 10:00 AM IST Opening Keynote

Keynote

SRIKANTH VELAMAKANNI, CO-FOUNDER, GROUP CHIEF EXECUTIVE & VICE-CHAIRMAN, FRACTAL


10:00 AM - 10:30 AM IST

10:00 AM - 10:30 AM IST Career Choices in AI and Analytics

Power Talk

AAMOD SATHE, DIRECTOR AND ANALYTICS LEAD - HOME AND WORK, META US

How do you think about your AI/Analytics career? Do you know where you stand? Like every good analysis the answers…

How do you think about your AI/Analytics career? Do you know where you stand? Like every good analysis the answers start with asking good questions. In this session, Aamod Sathe will share his thoughts on how to think about your careers. Aamod is a veteran of the analytics/AI industry with almost 20 years of experience in digital ads, fintech, product and marketing. Aamod currently leads analytics for Meta’s Reality Labs helping build the Metaverse.

Key Takeaways:

  • Careers are not destinations, they are journeys. The more you can plan and enjoy every step the more fulfilling your journey
  • Learn how the best technology companies think about AI/Analytics
  • Learn how to change your mindset to grow your analytics career


10:30 AM - 12:15 PM IST

10:30 AM - 12:15 PM IST No Active Session on Main-Stage


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


02:30 PM - 03:30 PM IST

02:30 PM - 03:30 PM IST Guinness World Records Attempt: Learn to Build an Artificial Intelligence Model with Kaggle Grandmasters

Guinness World Records Attempt Workshop

SUDALAI RAJKUMAR, HEAD OF AI & ML, GROWFIN.AI AND ROHAN RAO, SENIOR DATA SCIENTIST, H2O.AI

Have you ever wondered how to apply an artificial intelligence model to business problems? The focus of this session will…

Have you ever wondered how to apply an artificial intelligence model to business problems? The focus of this session will be on the machine learning pipeline including data cleaning, feature engineering, model building, evaluation, and productionization. Below is the outline of the proposed session.

We will start with an introduction to AI, Then proceed to a basic workflow of AI solutions, EDA with live coding, modeling with live code, model evaluation, and productionization.

Key Takeaways-

  • What is AI, how is it used, how has it progressed over the years, and where we are right now
  • A simple exploration of data, number of rows, column types, null values, mean target, feature distributions, correlations
  • Run a linear/logistic regression
  • Evaluate model accuracy, other useful metrics, etc.
  • Use a model to predict new test data
  • How AI helps in predictiveness, scale, progress, and innovation in the world


03:30 PM - 05:30 PM IST

03:30 PM - 05:30 PM IST Automated Machine Learning using PyCaret

Workshop

DIPANJAN SARKAR, LEAD DATA SCIENTIST, SIT ACADEMY

Low-code and Auto-ML are essential tools in a data scientist's toolbox to improve productivity and iterate faster in data science…

Low-code and Auto-ML are essential tools in a data scientist’s toolbox to improve productivity and iterate faster in data science projects. This hands-on workshop will focus on leveraging the popular open-source library PyCaret and go through learning essentials of how to use PyCaret to setup experiments, train, compare, tune, evaluate models and use them for predictions.
We will also go through an advanced notebook where we Learn advanced capabilities of PyCaret including data transformations, handling imbalanced data, advanced tuning methods, ensembling and using Explainable AI to interpret ML Models.
Key Takeaways:

  • Understand how to perform data science tasks using low code tool
  • Learn end-to-end use of Pycaret library


05:30 PM - 05:45 PM IST

05:30 PM - 05:45 PM IST Closing Note

Kavea Chavali

Closing Note by Host

Closing Note by Host


Timings


Sessions


10:45 AM - 12:15 PM IST

10:45 AM - 12:15 PM IST Exploring Network Clusters

Deep-Dive

ANAND S, FOUNDER AND CEO, GRAMENER

Clustering is an unsupervised learning algorithm that has a lot of value to add when it comes to the grouping…

Clustering is an unsupervised learning algorithm that has a lot of value to add when it comes to the grouping of data in a dataset. Entities in each group are comparatively more similar to entities of that group than those of the other groups. This talk explores network clustering as an approach for insights. We’ll explore real-world movie datasets — and show which actors are close to each other, and which film industries are most isolated. We’ll then see how network clustering can be applied to product networks, patent networks, and sports networks, and give you a comprehensive, industry-level understanding of the same.

Key Takeaways for the Audience:

  • How to get insights and patterns from the data even when there are no numbers
  • Understand network analysis and community structure detection
  • Understand applications of Network Analysis in the industry


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


01:00 PM - 02:30 PM IST

01:00 PM - 02:30 PM IST Model Monitoring Systems in Machine Learning

Deep-Dive

SAMIRAN ROY AND RAVI KUMAR

A common notion among starting data scientists is that the production deployment of the model is the end of the…

A common notion among starting data scientists is that the production deployment of the model is the end of the journey. In reality, there are never-ending ways in which the model can fail in production due to issues with the data, model, engineering, or human error. As business decisions are increasingly pivoting to being model-driven, the impact of these errors can have adverse real-world consequences. It is imperative to have a framework that continually monitors performance and technical debt and alerts the data scientist ahead/at the moment of potential failures.
This session is a practical what, why and how – of building such monitoring frameworks.

Key Takeaways from the session:

  • Example-based walkthrough on the best practices in model monitoring – covering both engineering and data aspects
  • How to set up a monitoring ecosystem, than encompasses sampling, setting up a tagging infrastructure, model versioning, and correct model interpretation
  • Practical techniques and algorithms to detect data and concept drift that allow us to track and keep the model healthy over time


Timings


Sessions


01:00 PM - 02:30 PM IST

01:00 PM - 02:30 PM IST Building Data Pipeline on AWS using Python and SQL

Deep-Dive

DURGA GADIRAJU, FOUNDER AND DIRECTOR, ITVERSITY CO-FOUNDER AND CTO, ANALYTIQS, INC.

Data Pipelines have enabled us to unlock the potential of utilizing big data. Companies are now able to optimize data…

Data Pipelines have enabled us to unlock the potential of utilizing big data. Companies are now able to optimize data transfer while securing it at the same time. With data collection, transformation, and transfer reaching new highs it had become necessary for companies to optimize costs and thus, shift this process to the cloud.
In this deep dive, we will build an end-to-end data pipeline using Python and SQL on AWS. You will be learning about several key services such as AWS s3, DynamoDB (for bookmarking), Cloudwatch (for monitoring), Lambda, ECR, Glue Catalog, Athena, etc along with Docker
Key Takeaways:

  • Architectural Overview of building end-to-end data pipeline using AWS Services
  • Deploy Complex Python applications as Lambda Functions
  • Build and Push custom Docker Images to ECR so that they can be used to configure Lambda Functions
  • Relevance of Bookmarking and Job Run Details using tables in Dynamodb
  • Configure s3-based Lambda Triggers


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


01:00 PM - 02:30 PM IST

01:00 PM - 02:30 PM IST Exploring Computer Vision and NLP with TensorFlow JavaScript

Deep-Dive

UMANG SHARMA

In this deep dive, we will create 2 web apps using TensorFlow JavaScript. The first will be a Deep learning…

In this deep dive, we will create 2 web apps using TensorFlow JavaScript. The first will be a Deep learning web app to play PacMan live and the other will be an NLP app for Sentiment Analysis.

We will begin with TF.js initially, and introduce its APIs. Then we proceed to the introduction of computer vision, the basics of Deep learning, MobileNet model. In the next part, we will learn the basics of NLP with Deep learning. We will talk about the basics of NLP such as One hot encoding, multi hot, tf-idf, and advanced topics such as Word Embedding, and LSTM. And then we will proceed with creating the apps.

Key Takeaways:

  • Deep learning with TensorFlow Javascript
  • Computer vision with Deep learning
  • NLP with Deep learning
  • Advanced Deep learning concepts such as Word Embedding, Depthwise convolutions, Transfer learning, and more


Timings


Sessions


10:45 AM - 12:15 PM IST

10:45 AM - 12:15 PM IST Hands-On Introduction to Time Series Forecasting

Deep-Dive

Dheeraj Singh


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


1:00 PM - 02:30 PM IST

1:00 PM - 02:30 PM IST Responsible AI

Deep-Dive

AKBAR MOHAMMAD, LEAD DATA SCIENTIST, FRACTAL AND SRAY AGGARWAL, PRINCIPAL CONSULTANT, FRACTAL

AI continues to influence our lives. From the trivial task of typing on our smartphones to personalized recommendations on shopping…

AI continues to influence our lives. From the trivial task of typing on our smartphones to personalized recommendations on shopping websites, intelligent machines are everywhere. Our interactions with technology are increasingly pushing the boundaries of ethics in AI. We will introduce you to the concerns the industry foresees and how we as practitioners and organizations can tackle the questions about fairness and equality, privacy, exploitation, environment, sustainability, and more.

Key Takeaways

  • Inspiring stories of AI
  • The dark side of AI today
  • What we can do to tackle some of these challenges
  • What perspective should we consider?
  • What can you do to activate responsible AI?


Timings


Sessions


09:45 AM - 10:30 AM IST

09:45 AM - 10:30 AM IST Product Thinking for Building Data Science Assets

Power Talk

ERIC WEBER, SENIOR DIRECTOR, STITCHFIX

Not everything we build in data science should be long lasting, but there are some investments that turn into long…

Not everything we build in data science should be long lasting, but there are some investments that turn into long term assets, necessitating careful management, development and improvement.

This session focuses on the value of product thinking for building data science assets. Given the “one-off” nature of many data science projects, Eric will focus on some ideas about how to identify when a data asset should become a product and how to manage it like one.

Key Takeaways:

  • How to initiate product thinking for building data science assets
  • Managing a product


10:30 AM - 12:15 PM IST

10:30 AM - 12:15 PM IST No Active Session on Main-Stage


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


02:30 PM - 03:00 PM IST

02:30 PM - 03:00 PM IST Riding the Flywheel of Recommender Systems

Power-Talk

DEBDOOT MUKHERJEE

Today recommender systems have an unprecedented influence on what content people consume on the internet and social media and what…

Today recommender systems have an unprecedented influence on what content people consume on the internet and social media and what products they purchase on e-commerce platforms. For many internet companies, their recommender system happens to be the key lever to trigger the flywheel on user growth as well as monetization.

This talk presents a high-level schematic overview of large-scale recommender systems. We will discuss effective training strategies for learning user and item representations and associated challenges in the state of the art. In particular, we deep dive into the perils of bias that can easily creep into the recommender systems and can often create a ceiling for their success. Finally, we emphasize why we need to balance the objectives of multiple stakeholders when recommenders are deployed in a marketplace in order to properly ride the flywheel.

Key Takeaways:

  • Recommender Systems and how they impact the flywheel of internet platforms
  • The high-level design of relevance systems
  • Techniques of representation learning
  • Common Biases and how to detect and address them
  • Balancing objectives for multiple stakeholders in a marketplace


03:00 PM - 04:30 PM IST

03:00 PM - 04:30 PM IST No Active Session on Main-Stage


04:30 PM - 05:00 PM IST

04:30 PM - 05:00 PM IST It Takes a Village to Raise AI

Keynote

D SCULLEY

Modern AI systems built on machine learning and massive data sets have shown incredible advances even in the most recent…

Modern AI systems built on machine learning and massive data sets have shown incredible advances even in the most recent years. But as our models grow exponentially larger, we find that many of the areas of ML technical debt grow more severe as well. And as the field of ML research continues to explode in popularity, it can become ever more difficult to separate signal from noise in published work. How can we know which models to choose to build on in production, and how can we gain sufficient trust and insights into their behavior?

One answer lies in the power of the community, where together we can achieve dramatically deeper levels of empirical rigor and stress testing than could ever be achieved by an individual or isolated group. In this talk, we will show some of the ways this is already being done by millions of passionate data scientists and machine learning practitioners — both novices and experts — and sketch out some of the opportunities ahead.


05:15 PM - 06:00 PM IST

05:15 PM - 06:00 PM IST AI Careers in 2030

Panel Discussion

KUNAL JAIN, AJOY SINGH, TAVISH SRIVASTAVA, AND DIPANJAN SARKAR


06:00 PM - 06:15 PM IST

06:00 PM - 06:15 PM IST Closing Note


Timings


Sessions


10:45 AM - 12:15 PM IST

10:45 AM - 12:15 PM IST Scalable ML Platform to Deploy a Recommendation System

Deep-Dive

ABHISHEK CHOUDHARY CO-FOUNDER TRUFOUNDRY, EX-FACEBOOK US, AND BADAL SINGH, FOUNDING ARCHITECT, TRUEFOUNDRY, EX-AMAZON US

While scaling machine learning platforms, key questions like Experiment Tracking, Deployment, Monitoring, Model to Frontend for easy Demoing, etc always…

While scaling machine learning platforms, key questions like Experiment Tracking, Deployment, Monitoring, Model to Frontend for easy Demoing, etc always confuse people. In this deep dive we will go through Scaling a machine learning platform by taking a Recommendation Model and using the platform to log and compare experiments in it.

Key Takeaways-

  • What are the key components of a ML System?
  • A Sample architecture of a ML Platform – personal experience of building TrueFoundry and choices
  • Using a platform to deploy a Recommendation model seamlessly through it
  • Thinking of and tracking your System metrics and what they mean


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


01:00 PM - 02:30 PM IST

01:00 PM - 02:30 PM IST Fine-tuning for Audio Classification with Transformers

Deep-Dive

JULIEN SIMON, CHIEF EVANGELIST, HUGGINGFACE, EX-AWS


3:00 PM - 4:30 PM IST

3:00 PM - 4:30 PM IST Supervised to Self Supervised Learning: A Step Towards Generalization with Reduced Labeled Data

Deep-Dive

NEHA BHARGAVA, SENIOR DATA SCIENTIST, FRACTAL

Self-supervised learning enables ML systems to learn from a huge amount of unlabeled data and generate powerful feature representations. In…

Self-supervised learning enables ML systems to learn from a huge amount of unlabeled data and generate powerful feature representations. In addition, many researchers believe that SSL could be a step toward how human intelligence works.

In this hands-on session, we will explore self-supervised learning and understand how it can address some of the limitations of supervised learning. We will implement supervised and self-supervised algorithms for the image classification tasks. And then compare the performances of both approaches in relation to labeled data quantity. The hope is to achieve similar or superior performance with the SSL counterpart using lesser labeled data!

Here are the key takeaways from the session:

  • Different types of learning (Supervised, Unsupervised, and Self-supervised)
  • Concepts of self-supervised learning
  • Introduction to the Image classification task
  • Implementation and comparison of one supervised model and its counter-self-supervised model
  • Industry examples where self-supervised learning is in action


Timings


Sessions


10:45 AM - 12:15 PM IST

10:45 AM - 12:15 PM IST Hands-on Introduction to AWS

Deep-Dive

Austin Noronha & Andres Diana


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


01:00 AM - 02:30 PM IST

01:00 AM - 02:30 PM IST AI-First Transformation in CPG Demand Planning and Forecasting

Deep-Dive

GUHA ATHREYA AND YADUNATH GUPTA

Consumer packaged goods (CPG) are items used daily by average consumers that require routine replacement or replenishment, such as food,…

Consumer packaged goods (CPG) are items used daily by average consumers that require routine replacement or replenishment, such as food, beverages, clothes, tobacco, makeup, and household products.

Predicting demand for this is a very crucial as each and every aspect of business from a manufacturers perspective depends on the accuracy of such predictions. This session will deep dive into AI-First Transformation in Consumer Packaged Goods Demand Planning and Forecasting.
Key Takeaways:

  • Demand Planning and Forecasting Challenges in CPG
  • Achieving superior forecasting accuracy using Deep Learning
  • Deep dive into forecasting model development using Deep Learning
  • Architecture (Hyper-parameter) tuning of complex deep learning architectures
  • Deep Learning models at scale
  • Qualifying Risk in Demand Planning – Enabling process transformation


03:00 PM - 04:30 PM IST

03:00 PM - 04:30 PM IST Predicting Machine Failures using Machine Learning

Deep-Dive

PRASHANT KARTIKEYA, SENIOR DATA SCIENTIST, EUGENE.AI


Timings


Sessions


09:45 AM - 01:00 PM IST

09:45 AM - 01:00 PM IST Analyzing US City Open data using Apache Spark

Workshop

RAGHU RAMAN AV, MENTOR , SUBJECT MATTER EXPERT - CLOUD BIG DATA AND EMERGING TECHNOLOGIES

In this session, we focus on learning the fundamentals of Apache Spark, one of the most popular Big Data Analytics…

In this session, we focus on learning the fundamentals of Apache Spark, one of the most popular Big Data Analytics tools. We start with a brief intro and dive right into an immersive hands-on session. The session focuses on exploring Spark as a Data Engineering tool by picking up an open dataset from US government data repository.

Key Takeaways:

  • Understand and appreciate Spark as an open-source tool for Big Data exploration
  • Get basic knowledge of working with Spark SQL
  • learn tricks to manipulate the data using graphs and charts


01:00 PM - 02:30 PM IST

01:00 PM - 02:30 PM IST Lunch Break


01:00 PM - 04:30 PM IST

01:00 PM - 04:30 PM IST Build a Text Classification Model

Workshop

RAGHAV BALI, STAFF DATA SCIENTIST, DELIVERY HERO

The amount of text data being generated in the world is staggering. Google processes more than 40,000 searches EVERY second!…

The amount of text data being generated in the world is staggering. Google processes more than 40,000 searches EVERY second! Analyzing patterns in that data can become daunting if you don’t have the right tools.

And with so much data being generated, interacting with artificial intelligent systems seems a bit simulated at times. This is because the way we converse as humans with one another is completely different from what we usually do with AI systems. Thankfully, research has been rampant in the area to bridge the gap in conversational AI systems.

In this workshop, we will cover a highly significant aspect of the Natural Language Processing (NLP) world-building a Text Classification model.

Key Takeaways:

  • Learn to build an end-end text classification model
  • Understand industry use cases of Text Classification
  • Understand how humans interact with an AI system


Timings


Sessions


09:15 AM - 10:00 AM IST

09:15 AM - 10:00 AM IST Ethics and Responsibility in the Age of AI

Keynote

DR. ROHINI SRIVATHSA

The pace at which artificial intelligence (AI) is advancing is remarkable. As we look out at the next few years,…

The pace at which artificial intelligence (AI) is advancing is remarkable. As we look out at the next few years, one thing is clear: AI will be celebrated for its benefits but also scrutinized and, to some degree, feared. It is crucial that for AI to benefit everyone, it is developed and used in ways that warrant people’s trust. Conversations around topics like fairness and privacy are important in the context of intelligent systems that are increasingly making decisions that thus far were only made by humans. These conversations are complex, contextualized and require the engagement of societies globally.
After offering the “Why”, this talk will outline a set of principles for defining ethics and responsibility in the age of AI: the “What”. While principles are necessary, having them alone is not enough. The hard and essential work begins when you endeavor to turn those principles into practices: the “How”. Building blocks for operationalizing responsible AI include tools and techniques, but also require practices, governance mechanisms, standards as well as policy and regulatory interventions. AI ethics and responsibility is an evolving field with people across industry, academia, governments, and policy makers actively engaged, and the talk will summarize some of the recent developments in this space.

Key Takeaways:

  • Why is ethics and responsibility in the age of AI a topic that requires everyone’s engagement?
  • What is responsible AI?
  • How to operationalize ethics and responsibility in AI, turn principles into practice?


10:00 AM - 10:30 AM IST

10:00 AM - 10:30 AM IST Bringing Intelligence to BI

Power Talk

RAJAT MONGA, CO-FOUNDER, CEO, INFERENCE.IO, EX-HEAD TENSORFLOW - DISTINGUISHED ENGINEER/SR. DIRECTOR, GOOGLE US

AI has seen a lot of advancements over the last decade. These are visible in consumer products such as the…

AI has seen a lot of advancements over the last decade. These are visible in consumer products such as the assistants – Alexa, Siri, OK Google – better experiences such as Photos, and in something billions of people use every day – Google Search. There’s also amazing research pushing science forward – AlphaGo beating the world champion at Go and AlphaFold mastering protein folding – the latter has a huge impact on future drug discoveries.
This talk will discuss how AI can help businesses as well, by leveraging their data to improve business performance and how AI is shaping the future of BI.

Key Takeaways-

  • How businesses are efficiently integrating AI to improve the customer experiences
  • The future of AI in business


10:30 AM - 12:15 PM IST

10:30 AM - 12:15 PM IST No Active Session on Main-Stage


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


2:30 PM - 3:00 PM IST

2:30 PM - 3:00 PM IST Analytics Translators- The New Superstars

Power Talk

MANI (SUBRAMANIAN M S), SR. DIRECTOR, MICROSOFT


03:00 PM - 04:30 PM IST

03:00 PM - 04:30 PM IST No Active Session on Main-Stage


04:30 PM - 05:00 PM IST

04:30 PM - 05:00 PM IST Learn About Recommendation Engines

DR. SARABJOT SINGH ANAND


05:00 PM - 05:15 PM IST

05:00 PM - 05:15 PM IST Closing Note

Closing Note

KUNAL JAIN, FOUNDER AND CEO ANALYTICS VIDHYA


Timings


Sessions


10:45 AM - 12:15 PM IST

10:45 AM - 12:15 PM IST Getting Quick Wins with Pre-Trained Models

Deep-Dive

RAJIV SHAH


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


1:00 PM - 2:30 PM IST

1:00 PM - 2:30 PM IST Conversation Design and Virtual Assistant Build

Deep-Dive

PALLAVI THAKUR, HEAD, CUSTOMER EXPERIENCE SENSEFORTH.AI AND KRISHNA N, LEAD, CONVERSATIONAL EXPERIENCE SENSEFORTH.AI

Conversational AI has phenomenally automated conversations at scale between people and organizations. It has transformed the way people buy and…

Conversational AI has phenomenally automated conversations at scale between people and organizations. It has transformed the way people buy and use products and services in a multi-experience world. In the deep-dive 1729 session, we give you a sneak view of what really goes into designing engaging and meaningful conversations that are helping global enterprises increase revenue and reduce costs. You would be experiencing the nuances, challenges and rewards of conversation design and how customer play a major role in this process.

Key takeaways:

  • Customer centricity in Conversational AI
  • Be introduced to the idea of NLP, NLU, NLG, intent identification, semantics
  • Experience of Conversational AI on various channels
  • SenseforthAI’s view of future of Conversational AI


3:00 PM - 4:30 PM IST

3:00 PM - 4:30 PM IST Saving Lives Across India: Behavioral Science Approach to Reducing Road Accidents

Deep-Dive

Alok Gangaramany, Principal Consultant, FinalMile Consulting

Road Safety approaches typically rely on technological solutions (e.g. improvement in cars) and regulations (e.g. fines, license requirements). However, it…

Road Safety approaches typically rely on technological solutions (e.g. improvement in cars) and regulations (e.g. fines, license requirements). However, it is estimated that over 90% majority of road fatalities are caused by human error. This has been the case in spite of many technological advancements such as Anti-lock braking systems, alert sensors, collision warning sensors, etc. Therefore understanding the behavioral drivers (emotions, mental models, biases) of these human errors is extremely important and can help us close this last mile issue and come up with impactful solutions.

The deep-dive will showcase real-world examples of solutions that have been implemented across 14 stretches of highways in India and their impact on reducing road accidents. We may also touch upon potential ways to integrate AI / ML on both the diagnosis and solutions front

Key Takeaways-

  • Understand why current technology cannot reduce road accidents
  • Why do the current behavioral approaches to improve the conscious awareness of the risks of poor driving continue to fall short
  • Understand why improvements in road infrastructure increase road accidents
  • Why don’t experienced drivers learn from their mistakes
  • Possibility of designing behaviorally informed Safe Roads
  • Understand how we use human emotions to reduce the risk of driving


Timings


Sessions


10:45 AM - 12:15 PM IST

10:45 AM - 12:15 PM IST Solving Taxi and Delivery Fleet Routing Problems with RL

Deep-Dive

DR. HARSHAD KHADILKAR, SENIOR DATA SCIENTIST, DATA AND DECISION SCIENCES, TCS RESEARCH

In this highly competitive taxi service industry, anticipating the location of future customer requests and accordingly selecting routes is critical…

In this highly competitive taxi service industry, anticipating the location of future customer requests and accordingly selecting routes is critical to gaining a competitive advantage. Such strategically selected routes would lead to shorter wait times for customers and reduced fuel costs for taxi drivers.
In this talk, we will discuss algorithms to achieve this goal both for the traditional scenario where a customer hires the entire taxi as well as the more recent ride-sharing model. Through extensive empirical evaluation of real datasets, we will present evidence that the proposed strategies lead to up to 70% shorter waiting times for customers, 40% more customers, and a 20% lower rejection rate.

Key Takeaways:

  • Efficient Route recommendation overview
  • Understanding how apt models reduce cost and increase revenue
  • Impact of Reinforcement learning on the cab-industry


12:15 PM - 01:00 PM IST

12:15 PM - 01:00 PM IST Lunch Break


1:00 PM - 2:30 Pm IST

1:00 PM - 2:30 Pm IST A/B Testing to Estimate a Product Feature Launch

Deep-Dive

ESHAN TIWARI, DATA SCIENCE LEAD, FACEBOOK


3:00 PM - 04:30 PM IST

3:00 PM - 04:30 PM IST Hands-On with Apache Airflow

SHARIQ AHMED KHAN


Timings


Sessions


10:00 AM - 01:00 PM IST

10:00 AM - 01:00 PM IST Build an Image Classification Model

Workshop

BHASKARJIT SARMAH


01:00 PM - 02:30 PM IST

01:00 PM - 02:30 PM IST Lunch Break


03:00 PM - 04:30 PM IST

03:00 PM - 04:30 PM IST Building an AI Pipeline using PyTorch

Deep-Dive

VISHNU SUBRAMANIAN