Elizabete Kalnozola Manager   •   about 4 years ago

HCL Technologies Problem Statements

HCL Technologies
Prize: Hiring Opportunities Mentor: Mojgan Ghanavati, Lead Data Scientist, HCL Technologies

Problem Statement:
1.Sentiment Analysis
Build a classifier to predict the sentiment of each sentence to positive vs negative sentiments. Three large review datasets from IMDB, Yelp, and Amazon labelled with positive or negative sentiment can be used in this exercise. Data - https://archive.ics.uci.edu/ml/datasets/Sentiment+Labelled+Sentences

2. Credit card defaults
Participants are expected to train an AI model that can predict the probability of customers default payments in Taiwan. From the perspective of risk management, the result of predictive accuracy of the estimated probability of default will be more valuable than the binary result of classification - credible or not credible clients. The data can be found in this link - https://archive.ics.uci.edu/ml/datasets/default+of+credit+card+clients

3.Diabetes is a huge concern area in today’s medical science. Hence, a close observation and prompt preventive / corrective measures are also necessary to have control over this concern. So, a Virtual Diabetes Advisor could be a good interface to take help from.

-Regular (in batch) update of Diabetic measures for all registered users.
-System would have defined thresholds depending on age, gender, demographics etc. Thresholds are also subject to revision periodically based on ML based trend analysis of Diabetic measures data.
-Within 5% range of the threshold, virtual advisor would send proactive voice-based communication to respective users with detailed advices over notification channels like WhatsApp.
-Users also can reach out to virtual advisor in both text as well as voice mode to seek help / advise / practitioners’ connect etc.
-The conversations can be audited, and the advisor wisdom can be auto upgraded with time.
-A Dashboard should be there to represent the healthcare data / conversation data.

Dataset https://archive.ics.uci.edu/ml/datasets/Diabetes