Publications by Analyze Core » R language
Twitter sentiment analysis with R
Recently I designed a relatively simple code in R to analyze the content of Twitter posts by using the categories identified as positive, negative and neutral. The idea of processing tweets is based on a presentation http://www.slideshare.net/ajayohri/twitter-analysis-by-kaify-rais. The algorithm evaluates tweets based on the number of posit...
2335 sym R (4219 sym/1 pcs) 4 img
Twitter sentiment analysis based on affective lexicons with R
Continue to dig tweets. After we reviewed how to count positive, negative and neutral tweets in previous post, I discovered another great idea. Suppose positive or negative is not enough and we want to understand the rate of positivity or negativity. For example, “good” in tweet has 4 points rating, but “perfect” has 6. Thus, we can try ...
1989 sym R (3899 sym/1 pcs) 4 img
Cohort analysis with R – “layer-cake graph”
Cohort analysis is one of the most powerful and demanded technique available to marketers for assessing long-term trends in customer retention and calculating life-time value. If you studied custora’s university, you could be interested by amazing “layer-cake graph” they propose for Cohort analysis. Custora says: “The distinctive “la...
2474 sym R (1362 sym/2 pcs) 6 img
Cohort analysis with R – “layer-cake graph” (part 2)
Continue to exploit great idea of ‘layer-cake’ graph. If you like approach I shared in previous topic, perhaps you have one or two questions we should answer. Recall “Total revenue by Cohort” chart : As total revenue depends on number of customers we attracted and on amount of money each of them spent with us, it has sense to dig dee...
2381 sym R (1965 sym/3 pcs) 8 img
Include promo/activity effect into the prediction (extended ARIMA model with R)
I want to consider an approach of forecasting I really like and frequently use. It allows to include the promo campaigns (or another activities and other variables as well) effect into the prediction of total amount. I will use a fictitious example and data in this post, but it works really good with my real data. So, you can adapt this alg...
6352 sym R (907 sym/1 pcs) 8 img
Cohort analysis with R – Retention charts
When we spend more money for attracting new customers then they bring us by the first but, usually, by the next purchases, we appeal to customer’s life-time value (CLV). We expect that customers will spend with us for years and it means we expect to earn some profit finally. In this case retention is vital parameter. Most of our customers a...
3767 sym R (3481 sym/5 pcs) 14 img
Shopping cart analysis with R – Multi-layer pie chart
In this post, we will review a very interesting type of visualization – the multi-layer pie chart – and use it for one marketing analytics task – the shopping cart analysis. We will go from the initial data preprocessing to the shopping cart analysis visualization. I will share the R code in that you shouldn’t write R code for every lay...
3336 sym R (3043 sym/11 pcs) 4 img
Sequence of shopping carts analysis with R – Sankey diagram
We studied how we can visualize the structure of a shopping cart in the previous post. Although you can find a great deal of materials on how to analyze combinations of products in the shopping cart (e.g. via association rules), there is a lack of sources on how to analyze the sequences of shopping carts. This post is an attempt to make up for th...
3233 sym R (2436 sym/10 pcs) 2 img
Sequence of shopping carts in-depth analysis with R
Although the sankey diagram from the previous post provided us with a very descriptive tool, we can consider it a rather exploratory analisys. As I mentioned, sequence mining can give us the opportunity to recommend this or that product based on previous purchases, but we should find the right moment and patterns in purchasing behavior. Therefore...
9304 sym R (6501 sym/18 pcs) 18 img
Sequence of shopping carts in-depth analysis with R – Clustering
This is the second part of the in-depth sequence analysis. In the previous post, we processed data to the required format, plotted a Sankey diagram, and did some distribution, frequency, time lapse and entropy analysis with visualization. For dessert, clustering! Clustering is an exploratory data analysis method aimed at finding automatically ho...
3257 sym R (708 sym/3 pcs) 8 img