top of page

Some of the Digital Analytics Methods

Translate the Analytics Findings into Useful Value Added Information

If you want to have conversation on some of these methods, please feel free to contact me but that will depend on how much time I have but will try to respond

Qualitative

  • Customer poll

  • Observation

  • Transactional

  • Interview

  • Survey

  • Panel

Semi-Quantitative

  • Scenario Analysis

Quantitative

  • Derived demand

  • Conjoint analysis

  • Trend fitting

  • Discrete choice models

  • Variance analysis

  • Contribution analysis

  • Causal forecasting

  • Projective forecasting

  • Decomposition analysis

  • Logit

  • Structural Equation

  • Multivariate Probit

  • Design of Experiment

  • Nonlinear Modeling

  • Bayesian Modeling

  • Markov Chain Monte Carlo Methods

  • Hierarchical Linear Models

  • Multinomial Probit Model

  • Stochastic Frontier

  • Principal components

  • Simultaneous equations modeling

  • Vector autoregressive models

  • ARMA models: the Box-Jenkins approach

  • Conjoint and Choice Analysis of what the customers want

  • Cluster analysis in market segmentation

  • Adstock model in effectiveness of advertising

  • Multidimensional scaling in customers’ idea points

  • The Predictive modeling include among others:

    • Modeling Trend and Seasonality

    • Copernican Principle to Predict Duration of Future Sales

    • Leveraging Neural Networks to Forecast Sales

  • The Mathematical based behavioral models include among others:

    • Monte Carlo Simulation and sensitivity analysis in terms of Marketing Decision Making

    • Calculating Lifetime Customer Value

    • Efficient Allocation of Resources in Customer Acquisition and Retention

    • Demand Curves with Solver to Optimize Price

    • Conditional probability in bundling and optimization in variance

  • Market Basket Analysis and Association Rule

  • OLAP and Data mining

Digital Analytics represents the opportunities to think like the customers, act like the customers and accurately predict when they will buy, what they will buy and where they will buy. A typical digital analytics team is positioned based on the availability and the benefits of big data to:

  • Research and Survey: Research, integrate and conduct custom primary research for more targeted, meaningful insights from  new value propositions through ideation to deliver best in the market to meet and exceed customers' expectations and generate additional revenue and profit

 

  • Predict Customer Buying Behavior: With advances in the field of  digital analytics, quantitative predictive analytics can be performed on the drivers, barriers, location and dynamics of customer buying behavior so as to generate predictive recommendations to improve marketing processes, products distinction, services uniqueness and marketing effectiveness.

    • Some of the quantitative analysis include Recency frequency monetary analysis (RFM), Propensity to buy, Postal Code Response Rates, Control Package Test, Prospect Profiles and Cluster analysis

 

  • User Experience: Customer Analytics provides our clients with deeper insights into their existing or prospective buyers and how best to retain them.

 

  • Segmentation: Quantitative analysis of customer location, buying power and behavior are leveraged to generate segmentation grid and allows for probability of movement from one grid to the other.

 

  • Market Demand Analysis: Qualitative and quantitative  analysis of the what the consumer wants or need: Time to call? How much will they pay? When will they pay? Who will best pay?

 

Please feel free to Contact me - Thanks, Stephen

bottom of page