Optimal free funds distribution for a large company

Client Issue

A large technology company was interested in the optimal placement of its available funds in banks. The solution needed to take into account both profitability and risk related to each bank and each deposit. The company idea was to gather all available data for banks of interest and turn it to valuable insights.

The stakeholder departments for this project were the Treasury department and the Risk Management department.

DAI Solution

Deloitte Analytics Institute developed a sophisticated system that utilises both wide domain banking expertise and machine learning algorithms that took into account data on banks performance and macroeconomics. DAI applied a multi-faceted approach towards achieving the customer’s goals, including the following steps:

  1. Problem framing

    Deloitte collected expectations, issues and requirements from the business departments and employees concerned. DAI specialists conducted interviews with stakeholders (business, risks, IT), clarified the requirements for the system and managed the client’s vision.
  2. Data collection and preprocessing

    Deloitte used data collected from Central Bank database and its proprietary database with world and Russian macroeconomic indicators. Examples of data used includes:
    • Banks’ standards (N0, N1, N2, etc.)
    • Specific product sales
    • Banks’ financial statements
    • Historical data on revoked licenses
    • Macroeconomics drivers (i.e., currency rates, industrial indexes, price indexes, etc.)

    This step included a data consistency check between different sources and inconsistency resolution, handling duplicates and null values, dictionary forming and transformation, the generation of new features, and calculation of statistics.

  3. Data processing and algorithm engineering

    Deloitte AI built a three-stage model that allows connections between changes in macroeconomics and certain aspects of banks’ financial performance to be established:
    • Forecasting macroeconomic indicators using a recurrent neural network – macroeconomics in this model is assumed to be a whole, highly connected and complex system.
    • Using macroeconomic indicators to predict certain aspects of banks’ financial performance. The model is based on linear models with regularisation and allows specific dependencies to be captured for each bank
    • Calculating the probability of licence revocation for different time intervals: half year, one year, three years. This model is based on machine learning algorithms performing classification tasks and allows threats for each bank to be identified.

    The outcome of this three-stage model is the revocation probability for each bank. Deloitte AI built a recommendation system for available fund placement that allows banks to maximise profits at fixed risk level.

Methods

  • Machine learning
  • Neural networks
  • Time series analysis
  • Econometrics

Outcomes

The completed system combined domain banking expertise and machine learning algorithms that use data on bank performance (Central Bank database) and macroeconomics (proprietary Deloitte database). The system allows for:

  1. The calculation of the licence revocation probability for the selected time horizon
  2. The optimisation of available fund placement in order to maximise profit at a fixed risk level

How our solution affects the Shareholder Value

Shareholder Value

  1. Revenue Growth
    1. Volume
      1. Acquire New Customers
      2. Retain & Grow Current Customers
      3. Leverage Income Generating Assets
    2. Price Realization
      1. Strengthen Pricing
  2. Operating Margin (after taxes)
    1. Selling General & Administrative (SG&A)
      1. Improve Customer Interaction Efficiency
      2. Improve Corporate/ Shared Service Efficiency
    2. Cost of Goods Sold (COGS)
      1. Improve Development & Production Efficiency
      2. Improve Logistics & Service Provision Efficiency
    3. Income Taxes
      1. Improve Income Tax Efficiency
  3. Asset Efficiency
    1. Property, Plant & Equipment (PP&E)
      1. Improve PP&E Efficiency
    2. Inventory
      1. Improve Inventory Efficiency
    3. Receivables & Payables
      1. Improve Receivalables & Payables Efficiency
  4. Expectations
    1. Company Strenghs
      1. Improve Managerial & Governance Effectiveness
      2. Improve Execution Capabilities
    2. External Factors