Use cases of Financial Data Science Techniques in retail

Financial domains like Insurance and Banking have uncertainty itself as an inherent product feature, and hence makes extensive use of Statistical models to develop, valuate and price their products. This presentation will showcase some of the techniques like Survival models and cashflow prediction models, popularly used in financial products, how can they be used in Retail data science, by showcasing analogies and similarities.

Survival models were traditionally used for modeling mortality, then got extended to be used for modeling queues, waiting time and attrition. We showcase, 1) How the waiting time aspect can be used to model repeat purchase behaviors of customers, and utilize the same for product recommendation on particular time intervals. 2) How the same survival or waiting time problem can be solved using discrete time binary response survival models (as opposed to traditional proportional hazard and AFT models for survival). 3) Quick coverage of other use cases like attrition, CLTV (customer lifetime value) and inventory management.

We show a use case where survival models can be used to predict the timing of events (e.g. attrition/renewal, purchase, purchase order for procurement), and use that to predict the timing of cashflows associated with events (e.g. subscription fee received from renewals, procurement cost etc.), which are typically used for capital allocation.

We also show how the backdated predicted cashflows can be used as baseline to make causal inference about strategic intervention (e.g. campaign launch for containing attritions) by comparing with actual cashflows post-intervention. This can be used to retrospectively evaluate the impact of strategic interventions.


Outline/Structure of the Talk

- Importance of Survival Regression techniques in modeling events and their timings in finance (3 mins)

- Discuss difference between event models and waiting time models (2 mins)

- Showcase traditional survival models and discrete time survival models solved through ensemble learning and ANN. Compare and show advantages, disadvantages (3 mins)

- Retail Use cases:

1. Product Recommendation using waiting time models: repeat purchase behavior as a function of waiting times between purchases and other factors (detailed showcase) (5 mins)

2. Customer Attrition models and CLTV (customer lifetime value models) -quick overview (1 min)

3. Inventory management using waiting time models and queuing theory (quick overview) (1 min)

- Cashflow models for subscription based retail businesses, and how it can be solved using survival models (3 mins)

- Causality analysis of Promotions/Campaigns using cashflow models

Learning Outcome

Audience will be benefited by understanding of what financial modeling techniques can be applicable to what kind of problems in retail

Target Audience

Data Scientists, Business Decision Makers, Data Analysts

Prerequisites for Attendees

Basics of machine learning techniques like ensemble learning, regression will be helpful.

schedule Submitted 1 year ago

  • Liked Samiran Roy

    Samiran Roy / Shibsankar Das - Algorithms that learn to solve tasks by watching (one) Youtube video

    45 Mins
    Case Study

    Imitation Learning has been the backbone of Robots learning from demonstrator's behavior. Join us to know more about How to train a robot to perform task like acrobatics etc.

    Two branches of AI - Deep Learning, and Reinforcement Learning are now responsible for many real-world applications. Machine Translation, Speech Recognition, Object Detection, Robot Control, and Drug Discovery - are some of the numerous examples.

    Both approaches are data-hungry - DL requires many examples of each class, and RL needs to play through many episodes to learn a policy. Contrast this to human intelligence. A small child can typically see an image just once, and instantly recognize it in other contexts and environments. We seem to possess an innate model/representation of how the world works, which helps us grasp new concepts and adapt to new situations fast. Humans are excellent one/few shot learners. We are able to learn complex tasks by observing and imitating other humans (eg: cooking, dancing or playing soccer) - despite having a different point of view, sense modalities, body structure, mental facility.

    Humans may be very good at picking up novel tasks, but Deep RL agents surpass us in performance. Once a Deep RL has learned a good representation [1], it is easy to surpass human performance in complex tasks like Go[2], Dota 2[3], and Starcraft[4]. We are biologically limited by time, memory and computation (A computer can be made to simulate thousands of plays in a minute).

    RL struggles with tasks that have sparse rewards. Take an example of a soccer playing robot - controlled by applying a torque to each one of its joints. The environment rewards you when it scores a goal. If the policy is initialized randomly (we apply a random torque to each joint, every few milliseconds) the probability of the robot scoring a goal is negligible - it won't even be able to learn how to stand up. In tasks requiring long term planning or low-level skills, getting to that initial reward can prove impossible. These situations have the potential to greatly benefit from a demonstration - in this case showing the robot how to walk and kick - and then letting it figure out how to score a goal.

    We have an abundance of visual data on humans performing various tasks, in the public domain, in the form of videos from sources like YouTube. In Youtube alone, 400 hours of videos are uploaded every minute, and it is easy to find demonstration videos for any skill imaginable. What if we could harness this by designing agents that could learn how to perform tasks - just by watching a video clip?

    Imitation Learning, also known as apprenticeship learning, teaches an agent a sequence of decisions through demonstration, often by a human expert. It has been used in many applications such as teaching drones how to fly[5] and autonomous cars how to drive[6] - It relies on domain engineered features - or extremely precise representations such as mocap [7]. Directly applying imitation learning to learn from videos proves challenging, there is a misalignment of representation between the demonstrations and the agent’s environment. For example: How can a robot sensing its world through a 3d point cloud - learn from a noisy 2d video clip of a soccer player dribbling?

    Leveraging recent advances in Reinforcement Learning, Self Supervised Learning and Imitation Learning [8] [9] [10], We present a technical deep dive into an end to end framework which:

    1) Has prior knowledge about the world intelligence through Self-Supervised Learning - A relatively new area which seeks to build efficient deep learning representations from unlabelled data but training on a surrogate task. The surrogate task can be rotating an image and predicting the rotation angle or cropping two patches of the image, and predicting their relative tasks - or a combination of several such objectives.

    2) Has the ability to align the representation of how it senses the world, with that of the video - allowing it to learn diverse tasks from video clips.

    3) Has the ability to reproduce a skill, from only a single demonstration - using applied techniques from imitation learning











  • Liked Karthik Bharadwaj T

    Karthik Bharadwaj T - Failure Detection using Driver Behaviour from Telematics

    45 Mins
    Case Study

    Telematics data have a potential to unlock revenue of 1.5 trillion. Unfortunately this data has not been tapped by many users.

    In this case study Karthik Thirumalai would discuss how we can use telematics data to identify driver behaviour and do preventive maintenance in automobile.

  • Liked Indranil Chandra

    Indranil Chandra - Data Science Project Governance Framework

    Indranil Chandra
    Indranil Chandra
    Assistant Manager
    schedule 1 year ago
    Sold Out!
    45 Mins

    Data Science Project Governance Framework is a framework that can be followed by any new Data Science business or team. It will help in formulating strategies around how to leverage Data Science as a business, how to architect Data Science based solutions and team formation strategy, ROI calculation approaches, typical Data Science project lifecycle components, commonly available Deep Learning toolsets and frameworks and best practices used by Data Scientists. I will use an actual use case while covering each of these aspects of building the team and refer to examples from my own experiences of setting up Data Science teams in a corporate/MNC setup.

    A lot of research is happening all around the world in various domains to leverage Deep Learning, Machine Learning and Data Science based solutions to solve problems that would otherwise be impossible to solve using simple rule based systems. All the major players in the market and businesses are also getting started and setting up new Data Science teams to take advantages of modern State-of-the-Art ML/DL techniques. Even though most of the Data Scientists are great at knowledge of mathematical modeling techniques, they lack the business acumen and management knowledge to drive Data Science based solutions in a corporate/MNC setup. On the other hand, management executives in most of the corporates/MNCs do not have first hand knowledge of setting up new Data Science team and approach to solving business problems using Data Science. This session will help bridge the above mentioned gap and help Executives and Data Scientists provide a common ground around which they can easily build any Data Science business/team from ground zero.

    GitHub Link ->

  • Liked Dr Hari Krishna Maram

    Dr Hari Krishna Maram - Future of Technology

    Dr Hari Krishna Maram
    Dr Hari Krishna Maram
    Vision Digital
    schedule 1 year ago
    Sold Out!
    20 Mins

    Future of Technology covered trends in technology across the globe and innovation changing the future