Worked  with  fraud  analytics  team  and  built  predictive  models  using  machine  learning 
techniques  to  determine  fraudulent  trades  in  equities,  forex  trades  and  wealth 
management related transactions.
Used ensemble of ML techniques like GBM, RF, NN, etc. to derive the best fit model.
Combination of AUC and balanced accuracy score was used to evaluate the models.

Worked on determining Model agents by regression, clustering and classification.
  Generated insights and results by segmenting agents into action groups  using statistical 
analysis and algorithms.
  Identified steps that each action group needs to take to  approach Model Agent.
  Ranked agents in each cluster based on the most appropriate criteria to determine their 
relative value in terms of business output.
  Provide  the  client  with  specific,  actionable  steps  to  share  with  the  agents  to  drive 
improved performance.

  Incident ticket analysis for various  platforms for identification of major issues and quick 
redressal
  Network analysis of ETL jobs to develop optimized alerting mechanism
  Identification  of  rows  majorly  accessed  by  analysts  so  as  to  purge  unwanted  data  for 
optimized query search and analysis

  Built algorithm for an online platform  to convert input in the form of natural language 
from user, generate appropriate SQL from it and return the desired result
  Used fuzzy string search and cosine distance to match the table and column names
  Developed Naïve Bayes classifier model to identify database based on user input
  Extracted table and column names mapped to appropriate SQL query based on database 
identified from classifier to return output.

  Developed  a  model  to  identify  a  future  complaint  depending  on  past  interactions  and 
transactions of the customer. 
  Formulated a mechanism to identify the mood of the customer and act proactively.
  Reduce the inflow of complaints in order to achieve more customer satisfaction.

Worked  on  building  a  data-driven  model to  provide supply-demand  forecasting  for  BC 
fulfilment needs.
  Built  R-shiny  app  for  taking  ad-hoc  requests  from  the  user  as  input  and  display  the 
scheduling period.
  Forecasted sales values for all accounts for the next one year and accordingly forecasted 
the Benefit Counsellors required.
 

  Worked on text processing for finding the root causes of server logs from ‘Service now’.
  Automated  the  entire  support  system  with  automated  ticket  classifier  using  machine 
learning which reduced the total effort by almost 70%. 
  Built a forecasting model to predict the hourly generation of tickets.
  Developed algorithm to generate alerts for long running jobs based on threshold values 
of durations