Campaign Data to Qualified Lead (Scoring)

 
In recent times, almost all organizations run campaigns (though they differ in their size, channel, type, audience, etc.,) all are aimed either loosely or strictly for demand generation in short/long term. Now due to variety, veracity and variability of such campaigns, campaign data lacks a unified view that can straightforwardly provide the set of metrics or values that are needed for qualified leads. It needs to be derived or identify the right set of data points from each channel / type, analyze what they mean (or measure against the goals), and then use that knowledge towards receptive marketable actions. Artificial Intelligence process involving unsupervised machine learning techniques help us arrive at better decisions reducing gap between desired and actual outcomes.

This blog/post attempts to explain in simple terms how to approach such diversified campaign data for marketing qualified leads scoring, it has two steps 1) identifying recurring patterns in the data (unsupervised machine learning), and 2) strategize similar segments for scoring using relative ranking.

Views expressed here are from author’s industry experience. Author trains/consults on Machine (Deep) Learning applications; for more details reach out at https://www.linkedin.com/in/pradeepmavuluri/

Nearest Neighbourhoods for forecasting of Fast Moving Consumer Goods (FMCGs)

 

Avoid Blind Supply Chain Practices during Covid-19 Crisis Times

Tip (3), Arrow, columnar (binary file) formats for both R and Python

Though Arrow was for around from some time (more than a year), in its recent release they came up with compression support that makes it be more user friendly for all data science activities across different languages. In my earlier posts, I have encouraged R users to use fst, however, in recent days, as Data Scientists frequency use both R and Python, an effective small files that can be easily read and write are useful in both development and testing phase.

In, my current testings where we are using a specific customer data of size about > 3 GB (CSV) for developing and testing a new algorithm, recent “arrow” version's write to parquet has yielded in half the size of R’s fst when compressed with “gzip” compressor. Similarly, results are obtained even with python.

--- Happy R & Python programming let me know your experiences.

Views expressed here are from author’s industry experience. Author trains and blog’s on Machine (Deep) Learning applications with various programming languages; for further details, he will be available at mavuluri.pradeep@gmail.com for more details. Find more about author at http://in.linkedin.com/in/pradeepmavuluri

Machine Learning (ML) helps in not wasting time in non responsive telemarketing calls

My last year post was more about how ML helped in identifying best time for telemarketing calls. This one on not wasting time in non responsive telemarketing calls.

Views expressed here are from author’s industry experience. Author trains on and blogs Machine (Deep) Learning applications; for further details, he will be available at mavuluri.pradeep@gmail.com for more details. Find more about author at http://in.linkedin.com/in/pradeepmavuluri

SKU Level Forecasting: Understanding Sales Segements

Understanding you sales segments especially when they are available at SKU level will help us achieving better forecasts. Look for following first, instead of reverse engineer with ML/Statistical techniques and wasting time in front.

1) Sales Variation - Foremost thing one should follow when we have SKU level data is to look for each SKU variability with respect to their average sales or from with in variation sales i.e. coefficient of variation.

  1a) In my practical journey of forecasting, I tend to look for zero ratio, which is nothing but, ratio of zero observations to non-zero observations. It tells us a lot about noise which we are going to face.

  1b) Also, I look for active, new and ended products, as most of the time clients never provide product life cycles and we combine all or treat all of them as same, forgetting the important impact of life cycle.

  1c) Further, in my practical journey of forecasting, I have seen lot of people, in reality failing to understand seasonal traits. Specific example, when seasonality moves from a time point to another (e.g. from one week to other, in cases of specific holidays like Good Friday and Easter). We need to get it right and label it right for modelling.

2) Client Provided Info - exploiting demographic or geographic information that already exists in the data. For instance, city information or product line/item information which makes it unique to that category.

3) Generate Segments - In few cases, I have observed that a bare minimum data about only date and time along with sales is provided for forecasting purposes. In such scenarios, we need to generate segments using unsupervised Machine Learning techniques, however, here, as said above, foremost start from sales variation obtained and proceed for better results.

Once all above, sales segment analysis is done, then job of identifying a better model is damn easy. For instance, a low volume with zeros SKU can be even predicted using a moving average method which provides better forecasting than high end boosting technique.

Views expressed here are from author’s industry experience. Author trains on and blogs Machine (Deep) Learning applications; for further details, he will be available at mavuluri.pradeep@gmail.com for more details.
Find more about author at http://in.linkedin.com/in/pradeepmavuluri

My Two Cents as pragmatic forecaster,
Happy Forecasting!