kind of problem recommender and rerolled it multiple times, making up dubious
excuses to justify, maybe you used some kind of problem recommender and rerolled it multiple
times, making up dubious
→ Pay attention
→ Top rated
| # | User | Rating |
|---|---|---|
| 1 | Benq | 3676 |
| 2 | Kevin114514 | 3659 |
| 3 | jiangly | 3640 |
| 4 | turmax | 3450 |
| 5 | tourist | 3408 |
| 6 | strapple | 3360 |
| 7 | Um_nik | 3354 |
| 8 | squareOf105 | 3348 |
| 9 | maroonrk | 3312 |
| 10 | idontwannadothis…e | 3191 |
→ Top contributors
| # | User | Contrib. |
|---|---|---|
| 1 | Qingyu | 154 |
| 2 | nik_exists | 151 |
| 3 | maspy | 149 |
| 4 | AmShZ | 146 |
| 5 | Um_nik | 143 |
| 6 | Errichto | 139 |
| 7 | BledDest | 136 |
| 8 | adamant | 135 |
| 9 | maroonrk | 133 |
| 10 | cry | 130 |
→ Find user
→ Recent actions
You can use several words in query to find by all of them at the same time. In addition, if you are lucky search understands word forms and some synonyms. It supports search by title and author. Examples:
305— search for 305, most probably it will find blogs about the Round 305andrew stankevich contests— search for words "andrew", "stankevich" and "contests" at the same timeuser:mikemirzayanov title:testlib— search containing "testlib" in title by MikeMirzayanov"vk cup"— use quotes to find phrase as istitle:educational— search in title
Results
1.
Self-deception: maybe why you're still grey after practicing every day I generally don't like to give much advice on "how to practice", but recently I have been thinking a lot about this and I realized that there is something that I believe affects a lot of people (though it is admittedly hard to tell) that barely gets talked about: self-deception.
Self-deception is a devious thing. It can be very hard to detect, yet can be fatal to improvement.
This blog is mainly directed to greys, greens and cyans that can't get out of these categories. Most examples are given with that in mind. That being said, I believe others have something to think about as well.
This is my first blog on such "psychological issues" and I don't know if I'll ever make another one. It's certainly a difficult topic to write about because for most of the blog, the message is "your practice is not as good as you think it is" or even "you aren't as good as you think you are" which can of course be a hard thing to hear. Thus, I have to somehow be very gentle while getting the poin...
2.
Ten years of Competitive Programming Hey Codeforces!
I’m AmirReza PourAkhavan, Codeforces Contest Coordinator. I let the story become complete and I’m sharing it now.
The story is about a 16-year competitive programmer, who left his family and migrated to another city alone to follow competitive programming. After seven years, he advanced to the International Collegiate Programming Contest World Finals, twice.
### Why I’m writing this
Six years ago someone asked me [here](https://codeforces.me/blog/entry/45186?#comment-297837) to write my story. I think it can help you to never give up.
### A brief about me
I've been doing competitive programming for ten years. I advanced to ICPC (International Collegiate Programming Contests) World Finals twice, in 2019 at Porto and 2020 at Moscow. At ICPC World Finals 2020, our team took high-honored place twenty-four, which is equal to the top 0.03% of 200k students participating in ICPC.
<center>
<br>
<img width="50%" src="/predownloaded/c2/0c/c20c501bba688...
am presenting in the ICPC World finals Porto, 2019: CP-connect, A problem
recommender., -connect, A problem recommender.
3.
CP trainer — a new tool for training Hello, <br/>
I created a project for training and analyzing your performance during contests: [cp-trainer.com](https://cp-trainer.com). I believe it has some unique features non-existent in competitive platforms and can provide as a more sensible tool for training, especially for more experienced users, who have participated already in a bunch of contests. Below I will briefly discuss its functionalities:
Problem recommender
------------------
In this section, we will discuss the heuristics used for problem recommender, the system offers for the user 10 problems with the highest value of this heuristics. First we need to introduce a couple of metrics:
<ul>
<li> <b> get_dict_accuracy </b> — Dictionary of form (<b>tag</b> : average number of submissions to accept problem with this tag during contest) </li>
<li> <b> ratings_average_time_diffs </b> — Dictionary of form (<b>rating</b> : average time in seconds to solve the problem with this rating during contest) </li>
<li...
functionalities: Problem recommender ------------------ In this section, we
will discuss the, Problem recommender ------------------ In this section, we will discuss the
heuristics used for, recommender.
* Weaknesses — The contest consists of 3 problems, all from topics, that user
4.
Codeforces problem recommender Hi all,
While practicing I always have difficulty choosing which problems to solve next. So, I coded a site to look at the user's submissions so far and recommend what all problems to solve next. Since the ICPC season is at peak now, it can also analyze multiple users and recommend practice problem for the whole team.
View the site here: [Code drills](http://code-drills.com).
So far, it only supports cf (EDIT: Now also supports codechef and spoj). I plan to add support for other sites later. Besides recommending, it will also show some statistics of your submissions so far. If you scroll down after entering your handle, you can view the practice recommendation. I will explain some of them here:
**ICPC**: Best to use this with team i.e. enter all your teammates' handles too. It will try to select problems from different topics. This and all other recommendations are based on your past submissions. So, the difficulty of the set will vary according to your past submissions (i...
Codeforces problem recommender
5.
Codeforces Upsolving Helper <spoiler summary="UPD(July 24, 2020)">**Randomize Button** added at the end of each section in **All Problemset Recommender** .
</spoiler>
<spoiler summary="UPD(July 19, 2020)">
**Unattempted Problem Recommender** from **Past Contests** (as suggested by [user:sharatsachin,2020-07-20] and [user:mr_robot11,2020-07-20]) and from **All Problemset** (as suggested by [user:ekaerovets,2020-07-23]) has been introduced .
</spoiler>
<spoiler summary="UPD(July 14, 2020)">
**Team Mode** has been introduced as suggested by [user:socho,2020-07-13].
</spoiler>
<spoiler summary="UPD(July 11, 2020)">
Rated and Unrated Problems are now separated under respective headings in each section(when Problems are segregated by Index) as suggested by [user:gol_en_05,2020-07-12] .
Hello, Codeforces community!
First of all, I would like to thank [user:MikeMirzayanov,2020-06-21] for such an awesome platform. It's been almost a year since I joined and ever since I was always in the dilemma which question to solve. It's a commonly accepted fact that one should solve the most solved questions first. Many other recommender websites out there follow the same pattern — solved count for the win. However, after some days of following it, it kinda felt repetitive. Yes, the ones that everyone can solve would be the easier ones. But how do we determine if it can teach us something new? Codeforces has the problem rating system which gives a more accurate view of which question is easy and which is not. But as with the case of solved counts, rating can't be considered as the sole differentiator.
After having analyzed for some time, I found that there are three important factors that decide which problem is best suitable for ...
accepted fact that one should solve the most solved questions first. Many other
recommender websites out, other recommender websites out there follow the same pattern — solved count
for the win. However
7.
rating-Aware problem recommender _Hi, I'm AmirMohammad (commonly known as **Danet**). Naturally, as a non-native speaker, the translation and editing process involved some assistance and **AI**. If you spot any technical or linguistic errors, I would be grateful if you pointed them out!_
#### personalized problem suggestions using reference sets
In competitive programming, one of the most common hurdles is selecting the right problems to practice. Standard random generators often suggest problems that are either too trivial or completely out of your league.
To solve this, we have been developing **@Lemiown_Bot**, a Telegram bot designed to suggest Codeforces problems precisely tailored to your current rating and learned topics. While standard bots pick uniformly from a rating range, our approach uses a **Reference Set** of high-rated users to ensure the quality and relevance of the suggested problems.
---
**The Reference Set ($S$):**
...
rating-Aware problem recommender
8.
CFRecommender — Personalized problem recommendation tool #### **UPDATE 2:**
-------------
Saving codeforces questions for **revision and upsolving** is now live on the [website](https://cfrecommender.vercel.app/).
1. Sign in with google so that no one else has access to your personal revision list.
2. Link your account to your codeforces handle by submitting a compilation error within 60 seconds.
3. Now you have access to create and edit your upsolve list. Add problems by just pasting a codeforces problem link and it will fetch the problem for you!
#### **UPDATE 1:**
-------------
There has been an overwhelming response from users worldwide, and I am very grateful for the same. I also received valuable feedback from a lot of you, and have tried imple...
rating, but also based on me. That was my motivation to build [CF Recommender
](https, That was my motivation to build [CF Recommender
](https://cfrecommender.vercel.app/). **It analyzes
9.
AlgoRadar: an explainable problem recommendation system for CP practice # AlgoRadar — an explainable recommender for CP practice
Hello Codeforces!
I built **AlgoRadar**, an open-source recommendation/analytics system for competitive programming practice.
Repository: [Link](http://github.com/drawmebaaz/AlgoRadar)
The goal is simple:
> Given my public submission history, what should I practice next?
The system uses Codeforces as the strongest source because it provides public submissions, verdicts, problem ratings, tags, rating history, and problemset metadata. It also has adapters for LeetCode and CodeChef, but Codeforces is the main difficulty anchor.
---
## 1. Main idea
AlgoRadar converts public CP activity into explainable features and ranks unsolved problems by **learning value**, not just rating or popularity.
Rough pipeline:
```
handle
-> fetch public submissions/problem metadata
-> build profile/tag/difficulty features
-> classify focus areas
-> estimate solve probability
-> rank candidate problems
-> buc...
because the recommender should not depend on transformer downloads or heavy
runtime dependencies., problems forever. So AlgoRadar uses it as **topic familiarity**, not as the
wholerecommender., # AlgoRadar — an explainable recommender for CP practice, The recommender first removes already solved problems:, This matters because a recommender can run without crashing and still give
misleading advice.
10.
Glimpse of a component in recommender algorithm and UI changes in CPDojo Recommender and Ladders Hi CF community,
Today I thought of sharing one of key components which is used by CPDojo recommender and CPDojo ladders. Ofcourse this is not the only ingredient used but this one plays an important key factor and may help other CPers to see and understand interesting patterns across problem ratings and rating groups.
As seen in the above image this shows how well participants in a specific ratingGroup benefits while solving a problem of particular rating. The higher the better. Maybe this gives you some insights and helps you in your practice !!
------------------------ UI / UX updates to CPDojo -----------------------------
1. Added functionality to mark solved problems in both Ladders and Recommender.
2. Also added progress bars to indicate your progress and how much percentage of the entire set you have completed. ( Maybe this provides you with some motivation to fully complete it :P )
 6 years ago and since then it has been used to recommend problems for practice more than **10 million** times! Unfortunately, over time, I got busy with other stuff and could not maintain it. Now I plan to open source the recommender so that it can be maintained by the community. For that I am looking for some volunteers from the competitive programming community.
CodeDrills has kindly agreed to continue to bear the hosting and other charges for the recommender.
More details [here](https://discuss.codedrills.io/t/looking-for-volunteers-to-open-source-and-maintain-codedrills-recommender/1810)
Let me know if you are interested in the same.
Cheers
Looking for volunteers to open source and maintain CodeDrills recommender, -maintain-codedrills-recommender/1810), CodeDrills has kindly agreed to continue to bear the hosting and other charges
for therecommender., We launched the CodeDrills [recommender](https://recommender.codedrills.io/) 6
years ago and since
12.
Problem Recommender System For Codeforces Users Hi Codeforces!
I am really pleased to introduce My research project called PROPER
- This is an web application that recommend you some problems that have adequate difficulty to practice.
After you solve the recommended problems you may give PROPER your feedback that the problem is Hard/Adequate/Easy.
This feedback will be used to make better recommender system.
- System automatically collect status data from CodeforcesAPI, and calculate adequate problems to user personally, Problem is recommended based on your status and other coder's status interactively.
- We use Matrix Factorization algorithm which is one of the famous recommender system model.
the PROPER address is: http://recommender.cf
I've evaluated this system in statistical way and it was quite good.
So I'd like to survey about this system for actual users.
I hope it works well for users and this system helps you practice better.
Thank you for reading!!
Problem Recommender System For Codeforces Users, is Hard/Adequate/Easy. This feedback will be used to make better recommender
system., - We use Matrix Factorization algorithm which is one of the famous recommender
system model., /Adequate/Easy. This feedback will be used to make better recommender system. -
System automatically
13.
Introducing Daily CF— Your Smart Problem Recommender for Codeforces Hey everyone!
=============
I’m excited to share something I’ve been working on — a Chrome extension called Daily CF.
It’s built to make your Codeforces practice more focused, consistent, and effortless by recommending daily personalized problems right inside the Codeforces interface.
### What is Daily CF?
Daily CF is a minimal, integrated extension that adds a new section named “→ CF Daily” to your Codeforces sidebar.
Every day, it suggests a small set of problems tailored to your current rating and problem history — so you can start solving instantly without wasting time deciding what to do next.
### Key Features
**Daily Personalized Problem Set**
Each day, Daily CF selects a fresh batch of unsolved problems near your current rating range using the Codeforces API.
You can also refresh manually anytime with the “Find”...
Introducing Daily CF— Your Smart Problem Recommender for Codeforces
14.
Recommender Hello guys, for those of you who are tired of searching for "what to solve next", my bachelor thesis was to implement a recommender system for competitive programming problems; supervised by Dr. Amr ElMougy and Maged Shalaby
Give it a look and check your recommendations now:
https://acm-recommender.herokuapp.com/#/signup
Sign-up (using your **codeforces username**) then sign-in and check your recommendations in almost no time (just give it a minute or 2).
There would be 10 problems recommended per user, we encourage you to solve them and give us feedback about each recommendation (through the "evaluate" button).
It is very important to **evaluate** the problems, as this feedback is needed to enhance the recommender and conclude which algorithm is better. So, please don't forget to submit your evaluations!
Thank you and happy coding.
For any problems or suggestions; you can contact me: [email protected]
Recommender, thesis was to implement a recommender system for competitive programming
problems; supervised by Dr. Amr, recommender and conclude which algorithm is better. So, please don't forget to
submit your evaluations!
15.
Feedbacks regarding CPDojo Recommendation system Hi CF community,
Recently I launched CPDojo problem recommendation system which recommends problems for a user so that they can reach their desired rating-group (next rating-group).
I just wanted to ask... did someone face issues where you clicked on 'Generate' button and you didn't get recommendations ?
Or any other issues / defects you found ? or want to give some different feedback regarding the recommended problems ?
Pls do let me know. Thank you !
Note: I'll use this blog to look into defects related to recommendation system.
Recommender can be found here : [here](https://www.cpdojo.com/recommender)
look into defects related to recommendation system. Recommender can be found
here : [here](https, Recommender can be found here : [here](https://www.cpdojo.com/recommender)
16.
Codeforces problems recommender I just found this website [Codeforces Recommender](https://cf-recommender.org/) that helps you find the perfect practice problems based on your rating. – Whether you're a beginner or pro, this site has so many recommendations that help push your coding skills to the next level!
You don't even need to sign up – just enter your handle and get instant suggestions. Plus, you can explore in guest mode too!
Codeforces problems recommender, I just found this website [Codeforces Recommender](https://cf-recommender.org/)
that helps you find
17.
Problem recommendation system (Local app based on XGBoost) 
After existing recommendation services shut down their servers, I built a fully offline Codeforces problem recommender.
- Data: Problems/submissions via Codeforces API
- Model: XGBoost predicting solve probability (local inference)
- App: Flutter with Hive database
Zero server dependency — everything runs on your device.
[Github Repository](https://github.com/nicotina04/cf-drills) | Windows OS build is [available](https://github.com/nicotina04/cf-drills/releases/tag/1.0.0%2B1)
problem recommender., recommendation services shut down their servers, I built a fully offline
Codeforces problemrecommender
18.
ML Based Rating Change Predictor and Problem Recommender Hello Codeforces,
I wanted to share this little project I made using ML to predict your ratings after the next 5 contests and recommend a few problems based on the predicted rating to help you grow based on your Top 3 weakest topics.
The project uses a Random Forest Regressor to learn patterns of different users in different rating ranges using factors like
1. Acceptance Ratio
2. Rating Trend
3. Tag Diversity
4. TagWise Success
Application Link: [cf-rating-predictor](https://cf-rating-predictor.netlify.app/)
GitHub Repo: [CFpredictor](https://github.com/Akshatt02/CFpredictor)
This is my first time implementing something ML-based so please forgive me if I did something wrong ;)
Thanks if you have any suggestions do let me know :)
ML Based Rating Change Predictor and Problem Recommender
Codeforces (c) Copyright 2010-2026 Mike Mirzayanov
The only programming contests Web 2.0 platform
Server time: Nov/11/2026 05:52:00 (k3).
Desktop version, switch to mobile version.
Supported by
