The documentation for the Watson Visual Recognition Services indicates that the costs for the service are
$0.25/Training image
$0.004 for classification per image per custom class
$10 for storage per custom class per month
So if I have 1 custom classifier with 1000 classes trained with 50 images each. Then the costs would be
$0.25 * 50000 = $12500 for initial training
$10 * 1000 = $10000 per month for storage
$4 per classification call if tested against all 1000 classes in the classifier
is my understanding correct? The $4 per call seems too high. Is the cost per class (1000 in this case) or per custom classifier (1 in this case)?
If I later add more training images (say additional 500 images), would the $0.25 per training image be charged for only these additional images ($0.25 * 500 = $125) or would it instead be $0.25 * 50500 = $12625?
This is a question for IBM Bluemix Support. You can open a support ticket at https://support.ng.bluemix.net/technicalsupport/. Stack Overflow is for technical programming questions.
Related
When choosing the Enterprise Plan for IBM Event Streams, there is a huge cost associated for Base Capacity Unit-Hour which costs more than $5K per month if I put 720 hours in it (assuming 1 month is 720 hours).
This makes it way too expensive and made me wonder if I understood correctly what "Base Capacity Unit-Hour" means.
Just got this from an IBM rep:
The price is 6.85/Base Capacity Unit, and that's by the hour. So broken down we have, 6.85 * 24 * 30 = 4932/month, which makes your estimate correct. Base Capacity Unit covers 150 MB/s(3 brokers) and 2TB storage. If you find you need to scale up, then the rate will increase from there.
I am desperately searching for an efficient way - if there is one - to solve some kind of a recursive task in T-SQL (I could successfully model it in excel and on paper with an iterative solution - as many CMAs would for a small example, re-allocating shares of cost between pairs of support units serving each other in iterations and minimising the balancing unit's unallocated cost leftover to a reasonably small number to stop iterations/recursion).
Now I am trying to find a good scalable solution (or at least a feasible approach to it) how to achieve the same in T-SQL for this typical computational task in the managerial accounting area: when some internal support units service each other (and incur periodic costs, like salary etc) to produce at the end let's say 2 or 3 final products together as a firm, and as a result their respective shares of internally generated support overheads need to be reasonably (according to some physical base distribution, lets say - man hrs spent in each) allocated to these products' cost at the end of the costing exercise.
It would be quite simple if there was no reciprocal services: one support unit providing some service to other support units during the period (and a need to allocate respective costs too alongside this service qty flow) and the second and third support units doing the same thing to other support peers, before all their costs get properly berried into production costs and spread between respective products they jointly serviced (not equally for all support units, I'm using activity-based-costing approach here)... And in a real case there could be many more than just 2-3 units one could manually solve in excel or on paper. So, it really needs some dynamic parameters algorithm (X number of support units servicing X-1 peers and Y products in the period serviced based on some qty-measure/% square matrix allocation table) to spread their periodic cost to one unit of each product at the end. Preferably, somehow natively in SQL without using external .NET or other assembly references.
Some numeric example:
each of 3 support units A,B,C incurred $100, $200, $300 of expenses in the period and worked 50 man hrs each, respectively
A-unit serviced B-unit for 10 hrs and C-unit for 5 hrs, B-unit serviced A-unit for 5 hrs, C-unit serviced A-unit for 3 hrs and B-unit for 10 hrs
The rest of the support units' work time (A-unit 35 hrs: 30% for P1 and 70% for P2, B-unit 45 hrs: 35% for P1 and 65% for P2, C-unit 37 hrs for P2 for 100%) they spent servicing the output of two products (P1 and P2); this portion of their direct time/effort easily allocates to products - but due to reciprocal services to each other some share of support units' cost needs to be shifted to a respective product cost pool unequal to their direct time to product allocation (needs an adjusted mix coefficient for step 2 effects).
I could solve this in excel with iterating algorithm and use of VBA arrays:
(a) vector of period costs by each support unit (to finally reallocate to products and leave 0),
(b) 2dim array/matrix of coefficients of self-service between support units (based on man hrs - one to another),
(c) 2dim array/matrix of direct hrs service for each product by support units,
(d) minimal tolerable error of $1 (leftover of unallocated cost in a unit to stop iteration)
For just 2 or 3 elements (while still manually provable on paper) it is a feasible approach, but this becomes impossible to manually prove for a correct solution once I have 10-20+ support units and many products in a matrix; and I want to switch from excel and VBA to MS SQL server and t-sql for other reasons.
Since this business case as such is not new at all, I was hoping more experienced colleagues could throw an advise how to best solve this - I believed there must have been a solution to this task before (not in pure programming environment/external code).
I am thinking to combine CTE(recursive), table variables and aggregate window functions - but hesitate/struggle how to best/exactly put all puzzle elements together so it is truly scalable for my potentially growing unit/product matrix dimensions.
For my current level it's a little mind blowing, so I'd be grateful for an advice.
I have a list of 7337 customers (selected because they only had one booking from March-August 2018). We are going to contact them and are trying to test the impact of these activities on their sales. The idea is that contacting them will cause them to book more and increase the sales of this largely inactive group.
I have to setup an A/B test and am currently stuck on the sample size calculation.
Here's my sample data:
Data
The first column is their IDs and the second column is the total sales for this group for 2 weeks in January (i took 2 weeks as the customers in this group purchase very infrequently).
The metric I settled on was Revenue per customer (RPC = total revenue/total customer) so I can take into account both the number of orders and the average order value of the group.
The RPC for this group is $149,482.7/7337=$20.4
I'd like to be able to detect at least a 5% increase in this metric at 80% power and 5% significance level. First I calculated the effect size.
Standard Deviation of the data set = 153.9
Effect Size = (1.05*20.4-20.4)/153.9 = 0.0066
I then used the pwr package in R to calculate the sample size.
pwr.t.test(d=0.0066, sig.level=.05, power = .80, type = 'two.sample')
Two-sample t test power calculation
n = 360371.048
d = 0.0066
sig.level = 0.05
power = 0.8
alternative = two.sided
The sample size I am getting however is 360,371. This is larger than the size of my population (7337).
Does this mean I can not run my test at sufficient power? The only way I can determine to lower the sample size without compromising on significance or power is to increase the effect size to determine a minimum increase of 50% which would give me an n=3582.
That sounds like a pretty high impact and I'm not sure that high of an impact is reasonable to expect.
Does this mean I can't run an A/B test here to measure impact?
Currently I'm building my monitoring services for my e-commerce Server, which mostly focus on CPU/RAM usage. It's likely Anomaly Detection on Timeseries data.
My approach is building LSTM Neural Network to predict next CPU/RAM value on chart trending and compare with STD (standard deviation) value multiply with some number (currently is 10)
But in real life conditions, it depends on many differents conditions, such as:
1- Maintainance Time (in this time "anomaly" is not "anomaly")
2- Sales time in day-off events, holidays, etc., RAM/CPU usages increase is normal, of courses
3- If percentages of CPU/RAM decrement are the same over 3 observations: 5 mins, 10 mins & 15 mins -> Anomaly. But if 5 mins decreased 50%, but 10 mins it didn't decrease too much (-5% ~ +5%) -> Not an "anomaly".
Currently I detect anomaly on formular likes this:
isAlert = (Diff5m >= 10 && Diff10m >= 15 && Diff30m >= 40)
where Diff is Different Percentage in Absolute value.
Unfortunately I don't save my "pure" data for building neural network, for example, when it detects anomaly, I modified that it is not an anomaly anymore.
I would like to add some attributes to my input for model, such as isMaintenance, isPromotion, isHoliday, etc. but sometimes it leads to overfitting.
I also want to my NN can adjust baseline over the time, for example, when my Service is more popular, etc.
There are any hints on these aims?
Thanks
I would say that an anomaly is an unusual outcome, i.e. a outcome that's not expected given the inputs. As you've figured out, there are a few variables that are expected to influence CPU and RAM usage. So why not feed those to the network? That's the whole point of Machine Learning. Your network will make a prediction of CPU usage, taking into account the sales volume, whether there is (or was) a maintenance window, etc.
Note that you probably don't need an isPromotion input if you include actual sales volumes. The former is a discrete input, and only captures a fraction of the information present in the totalSales input
Machine Learning definitely needs data. If you threw that away, you'll have to restart capturing it. As for adjusting the baseline, you can achieve that by overweighting recent input data.
I'm trying to review for my final and I'm going over example problems given to me by my professor. Can anyone explain to me the concept of how leaky bucket works. Also Here's a review problem my professor gave to me about leaky buckets.
A leaky bucket is at the host network interface. The data rate in the network is 2 Mbyte/s and the data rate from the application to the bucket is 2m5 Mbyte/s
A.) Suppose the host has 250 Mbytes to send onto the network and it sends the data in one burst. What should the minimum capacity of the bucket (in byte) in order that no data is lost?
B.) Suppose the capacity of the bucket is 100M bytes. What is the longest burst time from the host in order that no data is lost?
Leaky bucket symbolizes a bucket with a small hole allowing water (data) to come out at the bottom. Since the top of the bucket has a greater aperture than the bottom, you can put water in it faster that it goes out (so the bucket fills up).
Basically, it represents a buffer on a network between 2 links with different rates.
Problem A
We can compute that sending the data will take 250Mbyte / (2,5Mbyte / s) = 100 s.
During that 100 s, the bucket will have retransmitted (leaked) 100s * 2Mbyte/s = 200Mbytes
So the bucket will need a minimum capacity of 250MB - 200MB = 50MB in order not to lose any data
Problem B
Since the difference between the 2 data rates is 2.5MB/s - 2.0MB/s = 0.5MB/s, it means the bucked fills up by 0.5MB/s (when both links transmit at full capacity).
You can then calculate that the 100MB capacity will be filled after a burst of 100MB / 0.5MB/s = 200s = 3m 20s
Interesting problem - here's my attempt at solving A (no gurantees it's right though!)
So rate in = 2.5, rate out = 2.0, where the rate is in Mbyte/s.
So in 1 second, the bucket will contain 2.5 - 2.0 = 0.5 Mbyte.
1) If the host sends 250 Mbytes. This will take 100 seconds to transfer into the bucket at 2.5 Mbytes/s.
2) If the bucket drains at 2.0 Mbytes/s then it will have drained 100 * 2 = 200 Mbytes.
So I think you need a bucket which is 50 Mbytes capacity.